© 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. 15-LLAMASCOPE-RES-131K
    11. 87194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating simplicity or ease of action

    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
    imizer
    -0.08
    одеÑĢж
    -0.07
    chestra
    -0.07
    ød
    -0.07
    .nlm
    -0.07
    ennes
    -0.07
    vů
    -0.06
    zar
    -0.06
    nds
    -0.06
    phanumeric
    -0.06
    POSITIVE LOGITS
     dÃłng
    0.06
     easy
    0.06
    ulla
    0.06
    GD
    0.06
    jang
    0.06
     Gür
    0.06
    -thumbnails
    0.06
     Bah
    0.06
    095
    0.05
    erule
    0.05
    Activations Density 0.010%

    No Known Activations