© 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. 106068
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and regulatory documentation

    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
    zano
    -0.06
    otate
    -0.06
    大人
    -0.06
    ĵåIJį
    -0.06
     Raum
    -0.06
    à¥Ģय
    -0.06
     Ney
    -0.06
    ãĤĤãģ£ãģ¨
    -0.06
    kt
    -0.06
    assa
    -0.06
    POSITIVE LOGITS
    riel
    0.07
    ãĥ¼ãĥĦ
    0.07
    roll
    0.07
    hsi
    0.06
    zn
    0.06
    åŃ£
    0.06
    .reporting
    0.06
    osu
    0.06
    ration
    0.06
    moz
    0.06
    Activations Density 0.001%

    No Known Activations