© 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. 81868
    Prev
    Next
    INDEX
    Explanations

    instructions and processes related to technical troubleshooting and configuration

    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
     Lehr
    -0.07
    reon
    -0.07
    oine
    -0.07
    chwitz
    -0.07
    iday
    -0.07
    ÏĢοÏį
    -0.07
    dete
    -0.06
    åı²
    -0.06
    elligent
    -0.06
    aravel
    -0.06
    POSITIVE LOGITS
     circum
    0.07
     Temporary
    0.07
     temporarily
    0.07
     thủ
    0.07
     temporary
    0.07
    fid
    0.06
    íĹĮ
    0.06
    Temporary
    0.06
     hack
    0.06
    -disable
    0.06
    Activations Density 0.021%

    No Known Activations