© 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. 78742
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles related to individuals and organizations

    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
    antha
    -0.08
    lass
    -0.08
    logg
    -0.06
    ê²°
    -0.06
    lyph
    -0.06
    endant
    -0.06
    BU
    -0.06
    idor
    -0.06
     либо
    -0.06
    ãģĮãģĦ
    -0.06
    POSITIVE LOGITS
     who
    0.08
     which
    0.08
    which
    0.07
    who
    0.07
     involved
    0.07
     %,
    0.07
    ä½ľä¸º
    0.06
     representing
    0.06
     participating
    0.06
    avez
    0.06
    Activations Density 0.019%

    No Known Activations