© 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. 40190
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols in code-related contexts

    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
    argas
    -0.07
     STDCALL
    -0.07
    ofil
    -0.07
    reinterpret
    -0.07
    shaw
    -0.07
     YYS
    -0.07
     VÅ¡ech
    -0.06
    rim
    -0.06
    myp
    -0.06
    евÑĸ
    -0.06
    POSITIVE LOGITS
     int
    0.10
     boolean
    0.09
     bool
    0.09
    boolean
    0.08
    ITES
    0.07
     float
    0.07
    -fontawesome
    0.07
    .bool
    0.06
    strings
    0.06
     optional
    0.06
    Activations Density 0.029%

    No Known Activations