Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96192
    Prev
    Next
    INDEX
    Explanations

    phrases indicating participation or engagement in activities or events

    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
    uder
    -0.07
    i
    -0.06
    ÃŃt
    -0.06
    енÑĮ
    -0.06
    y
    -0.06
    en
    -0.06
    yne
    -0.06
    izzling
    -0.06
    olina
    -0.06
    asper
    -0.06
    POSITIVE LOGITS
    ruž
    0.08
     DeÄŁer
    0.08
    yms
    0.07
    inel
    0.07
    LLU
    0.07
    enticate
    0.07
    icens
    0.07
    å¢
    0.07
    oldur
    0.07
    errupted
    0.07
    Activations Density 0.006%

    No Known Activations