© 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. 92844
    Prev
    Next
    INDEX
    Explanations

    block structures used in programming or code syntax

    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
    swire
    -0.07
    avenport
    -0.07
    izzo
    -0.06
    rov
    -0.06
    omon
    -0.06
     Shapiro
    -0.06
    referer
    -0.06
    ãĥŃãĥ¼
    -0.06
    ofi
    -0.06
    uted
    -0.06
    POSITIVE LOGITS
    Brains
    0.07
    fos
    0.07
    busy
    0.06
    iaux
    0.06
     private
    0.06
    331
    0.06
    eyse
    0.06
    637
    0.06
    GRAM
    0.06
    private
    0.06
    Activations Density 0.005%

    No Known Activations