© 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. 117093
    Prev
    Next
    INDEX
    Explanations

    words related to a playful or humorous context

    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
    rst
    -0.07
    allis
    -0.06
    uft
    -0.06
    eworthy
    -0.06
    ater
    -0.06
    asant
    -0.06
    NAV
    -0.06
    optera
    -0.06
    icy
    -0.06
    VES
    -0.06
    POSITIVE LOGITS
    iven
    0.08
    [src
    0.06
    Äĥng
    0.06
    anas
    0.06
     sca
    0.06
    scape
    0.06
    ille
    0.06
    _management
    0.06
    roe
    0.06
     setting
    0.06
    Activations Density 0.005%

    No Known Activations