© 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. 58479
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and coding

    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
    ģında
    -0.07
    insk
    -0.07
    ĥģ
    -0.07
    ileo
    -0.07
    \Dependency
    -0.07
    rema
    -0.07
    reib
    -0.07
    myModal
    -0.07
    malink
    -0.07
    ucas
    -0.07
    POSITIVE LOGITS
     languages
    0.07
    -language
    0.07
    /script
    0.07
    erm
    0.06
     ç
    0.06
    /Admin
    0.06
    476
    0.06
    /design
    0.06
     Lesser
    0.06
    /stat
    0.06
    Activations Density 0.008%

    No Known Activations