© 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. 71494
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to cause, burden of proof, and the nature of controversies in legal contexts

    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
    _Pin
    -0.08
    ILED
    -0.08
    asje
    -0.08
    igits
    -0.08
     VÅ¡ech
    -0.07
    _integration
    -0.07
    uggy
    -0.07
    ADF
    -0.07
    ë¥
    -0.07
    LastError
    -0.07
    POSITIVE LOGITS
     sufficient
    0.07
     enough
    0.06
     Enough
    0.06
    ice
    0.06
    ure
    0.06
    ness
    0.06
     theory
    0.06
     requirement
    0.06
    ly
    0.06
    refs
    0.05
    Activations Density 0.043%

    No Known Activations