© 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. 87301
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and function definitions

    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
    monds
    -0.07
    robat
    -0.07
    ewis
    -0.07
    ucer
    -0.07
    uby
    -0.07
    иж
    -0.07
    nds
    -0.06
    ÅĽci
    -0.06
    acons
    -0.06
    usty
    -0.06
    POSITIVE LOGITS
     Cal
    0.05
     intermediate
    0.05
    formation
    0.05
     Flowers
    0.05
     Maiden
    0.05
     Signal
    0.05
     Meadow
    0.05
    ึ
    0.05
     Vice
    0.05
    _deinit
    0.05
    Activations Density 0.004%

    No Known Activations