© 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. 70895
    Prev
    Next
    INDEX
    Explanations

    critical phrases indicating game importance and playoff 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
    alette
    -0.06
     warrant
    -0.06
    .usermodel
    -0.06
    utsch
    -0.06
    onia
    -0.06
    AttributeValue
    -0.06
    icher
    -0.06
    ATTR
    -0.06
    arrant
    -0.06
     nga
    -0.06
    POSITIVE LOGITS
     importance
    0.08
     Importance
    0.07
     importante
    0.07
    ctest
    0.07
     imperative
    0.07
     ØŃس
    0.06
    igt
    0.06
     Gang
    0.06
    ondheim
    0.06
    .gs
    0.06
    Activations Density 0.017%

    No Known Activations