© 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. 62680
    Prev
    Next
    INDEX
    Explanations

    references to various formal or structured elements, such as components of a document or website

    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
    velt
    -0.07
    άνÏĦα
    -0.07
    oker
    -0.07
    Ïģκ
    -0.07
    ÑģÑĤеÑĢ
    -0.06
    ropp
    -0.06
    lus
    -0.06
    ushing
    -0.06
     ambit
    -0.06
    orary
    -0.06
    POSITIVE LOGITS
     yet
    0.08
     nÃło
    0.08
    yet
    0.07
    Yet
    0.07
    ductive
    0.06
    implify
    0.06
    elle
    0.06
    Found
    0.06
     forthcoming
    0.06
     existed
    0.06
    Activations Density 0.026%

    No Known Activations