© 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. 17835
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to organizations or concepts

    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
    EMENT
    -0.08
    umbn
    -0.08
    TURE
    -0.08
    RATION
    -0.07
    elig
    -0.07
    ECH
    -0.07
     EXEMPLARY
    -0.07
    ENTIAL
    -0.07
    E
    -0.07
    ERSION
    -0.07
    POSITIVE LOGITS
    s
    0.08
    aç
    0.07
    o
    0.07
    iT
    0.07
    U
    0.07
    oS
    0.07
    /OR
    0.07
    à¤ĵ
    0.07
    uffy
    0.07
    egend
    0.06
    Activations Density 0.309%

    No Known Activations