© 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. 128977
    Prev
    Next
    INDEX
    Explanations

    terms related to preventing negative consequences

    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
    zan
    -0.08
    thon
    -0.08
    atura
    -0.08
    THON
    -0.07
    aban
    -0.07
    .radioButton
    -0.07
    ibbon
    -0.07
    RIPTION
    -0.07
    egan
    -0.07
     isize
    -0.07
    POSITIVE LOGITS
     us
    0.09
    ively
    0.09
    /mit
    0.09
     from
    0.08
    oreach
    0.07
    ä¸įäºĨ
    0.07
    -motion
    0.07
    /re
    0.06
     others
    0.06
     being
    0.06
    Activations Density 0.015%

    No Known Activations