© 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 EvalsExportsAPI 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. 29346
    Prev
    Next
    INDEX
    Explanations

    references to dark themes and humor

    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
    ãĥĨãĥ«
    -0.07
    FINITE
    -0.07
    stime
    -0.06
    Forgery
    -0.06
    _managed
    -0.06
    898
    -0.06
    rypton
    -0.06
    aft
    -0.06
    resenter
    -0.06
    æĽ¸é¤¨
    -0.06
    POSITIVE LOGITS
    -dark
    0.09
     dark
    0.09
    dark
    0.08
     Dark
    0.08
     darken
    0.07
    -shadow
    0.07
    ened
    0.07
    Dark
    0.07
    ening
    0.07
    .Dark
    0.07
    Activations Density 0.016%

    No Known Activations