© 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. 106875
    Prev
    Next
    INDEX
    Explanations

    expressions of physical pain and injury

    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
    онов
    -0.07
    idot
    -0.07
    εÏĦ
    -0.06
    hta
    -0.06
     ↵↵
    -0.06
    =length
    -0.06
    _hpp
    -0.06
    _ASSUME
    -0.06
    mps
    -0.06
    ragen
    -0.06
    POSITIVE LOGITS
     pain
    0.07
    agus
    0.06
     radi
    0.06
    å¾
    0.06
    owie
    0.06
    819
    0.06
    Minor
    0.06
     rebel
    0.06
     right
    0.06
     during
    0.06
    Activations Density 0.014%

    No Known Activations