© 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. 126962
    Prev
    Next
    INDEX
    Explanations

    references to injuries and gunshot wounds

    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
    neau
    -0.08
    ادÙĨ
    -0.08
    irth
    -0.08
    umu
    -0.08
    tha
    -0.08
    ä½µ
    -0.08
    ButtonText
    -0.08
     fingert
    -0.07
    acht
    -0.07
    ollen
    -0.07
    POSITIVE LOGITS
     near
    0.07
     Binder
    0.06
     right
    0.06
     unprotected
    0.06
    .utility
    0.06
     Winds
    0.06
    ango
    0.06
     extrem
    0.06
     gel
    0.05
     leg
    0.05
    Activations Density 0.010%

    No Known Activations