© 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. 3980
    Prev
    Next
    INDEX
    Explanations

    terms related to precautions, challenges, and concepts of accountability

    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
    że
    -0.07
    andle
    -0.07
    lsen
    -0.06
    eron
    -0.06
    èµŀ
    -0.06
    kin
    -0.06
     jot
    -0.06
    esi
    -0.06
    /column
    -0.06
     Kidd
    -0.06
    POSITIVE LOGITS
    _Framework
    0.08
    prus
    0.07
     regarding
    0.07
    ìļ©
    0.07
    endance
    0.07
     Conc
    0.06
    -priced
    0.06
    ctp
    0.06
    à¸Ĺาà¸ĩà¸ģาร
    0.06
    824
    0.06
    Activations Density 0.044%

    No Known Activations