© 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. 17-LLAMASCOPE-RES-131K
    11. 77522
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly those indicating the end of statements or parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñĥже
    -0.06
    pa
    -0.06
    Ñĥж
    -0.06
     Rudd
    -0.06
     clim
    -0.06
     Oaks
    -0.06
    lw
    -0.05
    åģ¥
    -0.05
    åĬ©
    -0.05
    и
    -0.05
    POSITIVE LOGITS
    ugal
    0.07
    .IContainer
    0.07
    Ymd
    0.07
    swire
    0.07
    _svg
    0.07
    scoped
    0.07
    -wsj
    0.06
    _EXTENDED
    0.06
    ?type
    0.06
    rale
    0.06
    Activations Density 0.064%

    No Known Activations