© 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. 54109
    Prev
    Next
    INDEX
    Explanations

    specific terms and values related to measurements and statistics

    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
    /or
    -0.08
    .UnitTesting
    -0.07
    ancellationToken
    -0.07
    .omg
    -0.06
    /Instruction
    -0.06
    dra
    -0.06
    /gtest
    -0.06
    âĦ¢
    -0.06
    ®
    -0.06
    .EventArgs
    -0.06
    POSITIVE LOGITS
     lagi
    0.07
     veter
    0.07
    айд
    0.07
    EIF
    0.07
    ÙĮ
    0.07
    CJK
    0.07
    кид
    0.07
    CLU
    0.07
    ÅĻet
    0.06
    âĸ²
    0.06
    Activations Density 0.136%

    No Known Activations