© 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. 79290
    Prev
    Next
    INDEX
    Explanations

    occurrences of warnings and errors in code execution contexts

    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
    ÅĻes
    -0.07
    üç
    -0.07
    оÑī
    -0.06
    ç¦ģ
    -0.06
    лоÑĢ
    -0.06
     عاÙħÙĦ
    -0.06
     æį
    -0.06
    .mkdir
    -0.06
    elerin
    -0.06
    ÃĹ↵↵
    -0.06
    POSITIVE LOGITS
    747
    0.07
    ména
    0.06
    igy
    0.06
    ulfill
    0.06
    inea
    0.06
     unable
    0.06
    rotch
    0.06
    skirts
    0.06
     found
    0.06
    logic
    0.06
    Activations Density 0.027%

    No Known Activations