© 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. 1977
    Prev
    Next
    INDEX
    Explanations

    file extensions related to various data formats

    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
    cplusplus
    -0.07
    ỡ
    -0.06
     impr
    -0.06
    ked
    -0.06
    ä¿Ĭ
    -0.06
    çĶº
    -0.06
    گرÛĮ
    -0.06
    gre
    -0.06
    kas
    -0.06
    onda
    -0.06
    POSITIVE LOGITS
    .gz
    0.12
    .erb
    0.10
    .twig
    0.08
    roj
    0.07
     file
    0.07
    âĢİ
    0.07
     Gors
    0.07
    rette
    0.07
    swer
    0.07
    allon
    0.07
    Activations Density 0.034%

    No Known Activations