© 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 EvalsExportsAPI 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. 75090
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    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
    lop
    -0.06
    ox
    -0.06
     demonstr
    -0.06
    اÙģر
    -0.06
     Thames
    -0.06
    asu
    -0.06
    ält
    -0.06
     (*.
    -0.06
    pat
    -0.05
    ืà¸Ńà¸Ĥ
    -0.05
    POSITIVE LOGITS
    activex
    0.07
    -sdk
    0.07
     Emoji
    0.07
    .www
    0.07
    TRS
    0.07
    mvc
    0.06
     Cobra
    0.06
     Criterion
    0.06
     Reader
    0.06
    鬼
    0.06
    Activations Density 0.060%

    No Known Activations