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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 7-LLAMASCOPE-RES-32K
    11. 7995
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance and related formal attributes or disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relative
    -0.17
    relative
    -0.16
    rea
    -0.16
    amba
    -0.16
    bie
    -0.15
    rl
    -0.15
    rex
    -0.15
    aj
    -0.15
    ombo
    -0.14
    ione
    -0.14
    POSITIVE LOGITS
    iyat
    0.16
     FORMAT
    0.15
    oise
    0.15
    imat
    0.15
     ÐŀÑģÑĤ
    0.15
    erro
    0.15
    odash
    0.14
    ussy
    0.14
    requency
    0.14
    formats
    0.14
    Activations Density 0.013%

    No Known Activations