© 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. 15-LLAMASCOPE-RES-131K
    11. 90188
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets related to programming concepts

    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
     Qed
    -0.08
    weeney
    -0.07
    BufferData
    -0.07
    cast
    -0.07
    ActionCreators
    -0.06
    dea
    -0.06
    ertiary
    -0.06
    ãģĵ
    -0.06
     PROGMEM
    -0.06
    ustain
    -0.06
    POSITIVE LOGITS
     void
    0.08
    erdem
    0.07
     porr
    0.07
     int
    0.07
     inline
    0.07
    SError
    0.07
     bool
    0.06
    lineno
    0.06
    arium
    0.06
     Leslie
    0.06
    Activations Density 0.013%

    No Known Activations