© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17334
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic expression and its structural characteristics

    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
    ervers
    -0.07
     licens
    -0.06
    ackages
    -0.06
    enis
    -0.06
     multin
    -0.06
     legally
    -0.06
    licant
    -0.06
    egers
    -0.06
     travelers
    -0.06
    acie
    -0.06
    POSITIVE LOGITS
     Erotische
    0.07
    ANGO
    0.07
    ))==
    0.07
    ÑĪиб
    0.07
    *)((
    0.07
     Spiel
    0.07
    моÑģ
    0.07
    uhan
    0.07
    инкÑĥ
    0.07
    _ANDROID
    0.07
    Activations Density 0.023%

    No Known Activations