© 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. 18327
    Prev
    Next
    INDEX
    Explanations

    references to licensing and permissions related to content

    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
    ckill
    -0.08
    ãģĸ
    -0.07
     Fitz
    -0.06
    keit
    -0.06
    üzel
    -0.06
    itudes
    -0.06
    uez
    -0.06
    ellig
    -0.06
     altogether
    -0.06
    plr
    -0.06
    POSITIVE LOGITS
    ISC
    0.07
    isas
    0.06
    ç±
    0.06
    isa
    0.06
    RAND
    0.06
    .filters
    0.06
    fos
    0.06
    çľ
    0.06
    bar
    0.06
    kul
    0.06
    Activations Density 0.001%

    No Known Activations