© 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. 76225
    Prev
    Next
    INDEX
    Explanations

    references to coercion or compulsion

    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
    adf
    -0.07
    ry
    -0.07
    Ñİдж
    -0.07
    aar
    -0.07
    roperty
    -0.07
    xit
    -0.07
    /language
    -0.07
    ength
    -0.06
    pty
    -0.06
    Ä°T
    -0.06
    POSITIVE LOGITS
    ful
    0.08
    fully
    0.07
    evin
    0.07
    bow
    0.07
     Barr
    0.07
    ullo
    0.07
     Labor
    0.07
    ythe
    0.06
    Ĵáŀ
    0.06
     Vide
    0.06
    Activations Density 0.014%

    No Known Activations