© 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. 60953
    Prev
    Next
    INDEX
    Explanations

    code-related terms or commands associated with programming or scripting

    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
    äft
    -0.06
    åŁº
    -0.06
     culture
    -0.06
    _owned
    -0.06
    ervice
    -0.06
     architectural
    -0.06
    ernal
    -0.05
    arch
    -0.05
    ylko
    -0.05
     stage
    -0.05
    POSITIVE LOGITS
    .rdf
    0.07
    ignum
    0.07
    andid
    0.07
    croft
    0.07
    iyim
    0.07
    icals
    0.07
    ÑĢиз
    0.07
     Gros
    0.07
    gency
    0.06
    .compiler
    0.06
    Activations Density 0.022%

    No Known Activations