© 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. 78124
    Prev
    Next
    INDEX
    Explanations

    code-related terms and syntax elements in programming 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
    datal
    -0.06
     Voy
    -0.06
    ulary
    -0.06
     SCI
    -0.06
    SCI
    -0.06
    _traits
    -0.06
    chi
    -0.06
     ï½ľ
    -0.06
    960
    -0.06
     lyon
    -0.06
    POSITIVE LOGITS
    @api
    0.08
    ASTER
    0.07
    jit
    0.07
    _Tree
    0.07
     ERP
    0.06
    dna
    0.06
     Od
    0.06
    xml
    0.06
     Precision
    0.06
    ERP
    0.06
    Activations Density 0.013%

    No Known Activations