© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93567
    Prev
    Next
    INDEX
    Explanations

    references to the human body and its anatomical features

    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
     kariy
    -0.07
     Aura
    -0.07
    grounds
    -0.07
    _TOOLTIP
    -0.07
    UGH
    -0.07
    ãģĵ
    -0.07
    _:*
    -0.07
    åijĬ
    -0.06
    ç¸
    -0.06
    ÑģÑĥÑĤ
    -0.06
    POSITIVE LOGITS
    requires
    0.07
    æĿ¥è¯´
    0.07
     purposes
    0.07
     sake
    0.07
     Require
    0.06
    Requires
    0.06
     consult
    0.06
     required
    0.06
     use
    0.06
     require
    0.06
    Activations Density 0.042%

    No Known Activations