© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 31697
    Prev
    Next
    INDEX
    Explanations

    the word "Even" and its variations, indicating a focus on expressions of contrast or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Even" at the beginning of a sentence or clause, particularly when introducing a contrasting or concessive statement.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    sentence-initial concessive adverbs that introduce an emphatic or contrastive clause.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aurus
    -0.15
     either
    -0.15
     Strait
    -0.15
    Either
    -0.15
     Either
    -0.15
    aska
    -0.15
     anywhere
    -0.14
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.14
    Anywhere
    -0.14
    adir
    -0.14
    POSITIVE LOGITS
     though
    0.21
    Though
    0.18
    though
    0.18
     wenn
    0.16
    ough
    0.16
    .jpa
    0.15
    when
    0.15
    ija
    0.15
     Though
    0.15
     staunch
    0.15
    Activations Density 0.022%

    No Known Activations