© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29555
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and syntax

    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
    raries
    -0.07
    оÑģÑĢед
    -0.07
    isz
    -0.07
    оби
    -0.07
    ilo
    -0.07
    ucci
    -0.06
     ввод
    -0.06
     Coff
    -0.06
    ielding
    -0.06
    arro
    -0.06
    POSITIVE LOGITS
     Laden
    0.07
    argout
    0.06
    NST
    0.06
    iona
    0.06
    DebugEnabled
    0.06
    nex
    0.06
     qua
    0.06
     explor
    0.06
    Dear
    0.06
    istrovstvÃŃ
    0.05
    Activations Density 0.001%

    No Known Activations