© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75144
    Prev
    Next
    INDEX
    Explanations

    specific references to conditions or operations involving logic or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Short tokens with syntactic rather than semantic meaning, often appearing in mathematical notation or at structural boundaries in text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ced
    -0.06
    allis
    -0.06
    ãĥ»ãĥ»ãĥ»↵↵
    -0.06
     út
    -0.06
    ango
    -0.06
    Blo
    -0.06
    acades
    -0.06
     Swinger
    -0.06
     -=
    -0.06
    Browsable
    -0.06
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.13
    ÌĨ
    0.10
    Ìģ
    0.07
    ÌĪ
    0.07
    porno
    0.07
    leftright
    0.07
    ÌĢ
    0.07
    Ì
    0.07
    iqueta
    0.07
    :///
    0.06
    Activations Density 0.508%

    No Known Activations