© 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. 15-LLAMASCOPE-RES-131K
    11. 88680
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords in a technical 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
    .cx
    -0.07
    ondon
    -0.06
    oden
    -0.06
    eree
    -0.06
    908
    -0.06
    opak
    -0.06
     Ler
    -0.06
     ngu
    -0.06
    ielding
    -0.06
     portions
    -0.06
    POSITIVE LOGITS
    ahl
    0.07
     èı
    0.07
    atisfied
    0.07
    lege
    0.07
     Fet
    0.07
    овеÑĢ
    0.06
    ink
    0.06
    инок
    0.06
    .setResult
    0.06
    .PageSize
    0.06
    Activations Density 0.008%

    No Known Activations