© 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 EvalsExportsinterp-engineNEWAPI 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. 86324
    Prev
    Next
    INDEX
    Explanations

    the presence of specific numeric statistics and identifiers

    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
     cref
    -0.08
    olicited
    -0.07
    POCH
    -0.07
    Å¡ka
    -0.07
     fov
    -0.06
    bach
    -0.06
    oldt
    -0.06
    MAIL
    -0.06
    ivec
    -0.06
    wand
    -0.06
    POSITIVE LOGITS
    jab
    0.06
    'gc
    0.06
    ãĢħ
    0.06
    silver
    0.06
    楽
    0.06
    tridge
    0.05
    ypad
    0.05
     Haram
    0.05
     combo
    0.05
    ãĥ§
    0.05
    Activations Density 0.000%

    No Known Activations