© 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. 76348
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court documents

    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
    569
    -0.08
    783
    -0.07
    unan
    -0.07
    chal
    -0.07
    itori
    -0.07
    rech
    -0.07
    reff
    -0.07
    steen
    -0.07
    ADVERTISEMENT
    -0.07
    cec
    -0.07
    POSITIVE LOGITS
    uis
    0.06
    imp
    0.06
     rule
    0.06
    apor
    0.05
    usat
    0.05
     Kov
    0.05
    лÑĥг
    0.05
    ospace
    0.05
    ornings
    0.05
     partition
    0.05
    Activations Density 0.016%

    No Known Activations