© 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. 85344
    Prev
    Next
    INDEX
    Explanations

    references to classes and their attributes in a programming context

    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
    .MixedReality
    -0.08
    .Charting
    -0.07
    ioc
    -0.07
     SqlDbType
    -0.07
     Tro
    -0.07
    ÑĥÑĪ
    -0.07
    ollar
    -0.06
    ingly
    -0.06
    ocracy
    -0.06
    raphic
    -0.06
    POSITIVE LOGITS
    aklı
    0.07
    asure
    0.06
    -corner
    0.06
    ince
    0.06
     builtin
    0.06
    .Decode
    0.06
    .diff
    0.06
    laden
    0.06
     stir
    0.06
    /OR
    0.06
    Activations Density 0.001%

    No Known Activations