© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    topics related to work ethic and the impact of helpfulness

    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
     Kinh
    -0.07
    iyim
    -0.07
    à¥ĩà¤ķर
    -0.07
    ĤŃ
    -0.07
    alars
    -0.07
    276
    -0.07
    ''"
    -0.07
    èĻŁ
    -0.07
    argout
    -0.07
     COPYRIGHT
    -0.07
    POSITIVE LOGITS
    power
    0.07
     everything
    0.06
     power
    0.06
     Ub
    0.06
    -power
    0.06
    POWER
    0.06
    åĬĽ
    0.06
    innamon
    0.06
    bers
    0.06
     alone
    0.06
    Activations Density 0.032%

    No Known Activations