© 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. 87607
    Prev
    Next
    INDEX
    Explanations

    boolean values and their states in coding 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
    ichtig
    -0.06
    ToLeft
    -0.06
     Vak
    -0.06
    HELL
    -0.06
    tent
    -0.06
    SEL
    -0.06
     excess
    -0.06
     fik
    -0.06
    _strerror
    -0.06
    LIK
    -0.05
    POSITIVE LOGITS
    Already
    0.07
     Locker
    0.07
    еÑī
    0.07
     already
    0.06
    _Api
    0.06
    ÑĢд
    0.06
     Already
    0.06
    acci
    0.06
    usch
    0.06
    hind
    0.06
    Activations Density 0.019%

    No Known Activations