© 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. 75130
    Prev
    Next
    INDEX
    Explanations

    instances of "inline" code declarations or parameters in coding 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
    ekk
    -0.08
    Ñĥка
    -0.07
    ooks
    -0.07
    builtin
    -0.07
    fleet
    -0.07
    ách
    -0.07
    iel
    -0.07
    از
    -0.07
    weeney
    -0.07
    άκ
    -0.07
    POSITIVE LOGITS
     void
    0.08
    297
    0.06
    est
    0.06
    ropa
    0.06
    ADE
    0.06
    lox
    0.06
    uge
    0.06
    348
    0.05
    788
    0.05
    auen
    0.05
    Activations Density 0.006%

    No Known Activations