© 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. 92803
    Prev
    Next
    INDEX
    Explanations

    structural elements or annotations in a programming or markup 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
     addCriterion
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    artisan
    -0.06
    vailability
    -0.06
    .Apis
    -0.06
    argon
    -0.06
    rike
    -0.06
    ÏĢε
    -0.06
    atten
    -0.06
    .ErrorMessage
    -0.06
    POSITIVE LOGITS
    ition
    0.07
    kaç
    0.06
    RTL
    0.06
    vu
    0.06
    SOAP
    0.06
    elli
    0.06
    isers
    0.06
    оÑģÑĥд
    0.06
     Tüm
    0.06
    aces
    0.06
    Activations Density 0.000%

    No Known Activations