© 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. 106457
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "use" and associated legal terminology

    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
    acam
    -0.07
    heim
    -0.07
    amera
    -0.06
    ç·Ĵ
    -0.06
    zte
    -0.06
    ullah
    -0.06
    ÑĴ
    -0.06
    loon
    -0.06
    út
    -0.06
     exhausting
    -0.06
    POSITIVE LOGITS
    mA
    0.07
    ager
    0.07
     पड
    0.06
     Rewards
    0.06
    uge
    0.05
    amble
    0.05
    lund
    0.05
    ìĹ°
    0.05
     od
    0.05
    _progress
    0.05
    Activations Density 0.003%

    No Known Activations