© 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. 75047
    Prev
    Next
    INDEX
    Explanations

    instances of comments or annotations in a code document

    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
    ziel
    -0.07
    nesota
    -0.07
    PTION
    -0.07
    pto
    -0.06
    sd
    -0.06
    ãĥ³ãĤº
    -0.06
    igans
    -0.06
    ÃŃme
    -0.06
    еле
    -0.06
    ľ´
    -0.06
    POSITIVE LOGITS
    HttpException
    0.06
    ãģªãĤĵãģł
    0.06
     leg
    0.06
    zung
    0.06
    -thumbnail
    0.06
    ssp
    0.06
    .netbeans
    0.06
     Brain
    0.06
    iken
    0.06
    -leg
    0.06
    Activations Density 0.003%

    No Known Activations