© 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. 16304
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions particularly in the context of formulas or equations

    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
    etary
    -0.08
    gres
    -0.06
    et
    -0.06
     Higgins
    -0.06
    EventArgs
    -0.06
    OrFail
    -0.06
    oo
    -0.06
    ope
    -0.06
    ek
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
    soever
    0.07
    à¸ľ
    0.07
    oenix
    0.07
    è¢ĸ
    0.07
    ÑĸллÑı
    0.07
    athe
    0.07
    lier
    0.07
    è¥
    0.07
    HeaderCode
    0.07
    orientation
    0.06
    Activations Density 0.001%

    No Known Activations