© 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. 9-LLAMASCOPE-RES-131K
    11. 95591
    Prev
    Next
    INDEX
    Explanations

    terms related to sports and players, particularly in hockey

    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
    aliz
    -0.07
    stad
    -0.07
    incinn
    -0.07
    stadt
    -0.07
    umpt
    -0.07
    kinson
    -0.07
    aeper
    -0.07
    peri
    -0.06
    rogen
    -0.06
    azzo
    -0.06
    POSITIVE LOGITS
    645
    0.07
     :::
    0.06
    jur
    0.06
    Ø¢ÙĨ
    0.06
     cha
    0.06
     toJSON
    0.06
    agan
    0.06
    vor
    0.06
    aki
    0.05
     Rap
    0.05
    Activations Density 0.002%

    No Known Activations