© 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. 3438
    Prev
    Next
    INDEX
    Explanations

    elements related to racing events and their dynamics

    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
     nackte
    -0.08
    ubby
    -0.08
    overrides
    -0.07
    ulkan
    -0.07
    inizi
    -0.07
    /Gate
    -0.07
    emme
    -0.07
    icros
    -0.07
    ub
    -0.07
    ÎŃÏģα
    -0.07
    POSITIVE LOGITS
     soon
    0.06
    daq
    0.06
    ev
    0.06
     seconds
    0.06
    314
    0.06
    unde
    0.06
     behind
    0.06
    rid
    0.06
    oni
    0.06
    nav
    0.05
    Activations Density 0.006%

    No Known Activations