© 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. 117712
    Prev
    Next
    INDEX
    Explanations

    comments in code

    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
    osta
    -0.07
    770
    -0.06
    ossa
    -0.06
    ReuseIdentifier
    -0.06
    ma
    -0.06
    庫
    -0.06
    669
    -0.06
    385
    -0.06
    ibbon
    -0.06
    icode
    -0.06
    POSITIVE LOGITS
    /goto
    0.07
    oola
    0.07
    clamp
    0.07
     Clamp
    0.07
    seo
    0.07
    urette
    0.06
    getID
    0.06
    umer
    0.06
    ulse
    0.06
    ÃŁer
    0.06
    Activations Density 0.001%

    No Known Activations