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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 2464
    Prev
    Next
    INDEX
    Explanations

    the verb "are" as an indicator of present tense states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hayward
    -0.17
    mercial
    -0.16
    bsub
    -0.15
    .lp
    -0.15
    erville
    -0.15
    .sponge
    -0.15
    گز
    -0.15
    ãĥIJãĤ¤
    -0.15
    šov
    -0.14
     гоÑĤ
    -0.14
    POSITIVE LOGITS
     Mens
    0.17
     dost
    0.16
     md
    0.15
    rych
    0.15
    eton
    0.15
     mt
    0.15
    mts
    0.15
    ich
    0.14
    kn
    0.14
     Cust
    0.14
    Activations Density 0.022%

    No Known Activations