© 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. 1859
    Prev
    Next
    INDEX
    Explanations

    references to spaces associated with players in sports, particularly locker and dressing rooms

    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
    UNET
    -0.09
     DUP
    -0.08
    aná
    -0.08
    ÙħÛĮÙĨ
    -0.08
     âĸ³
    -0.07
    (æ°´
    -0.07
    ıb
    -0.07
    sik
    -0.07
    sing
    -0.07
    íĥĿ
    -0.07
    POSITIVE LOGITS
    oom
    0.07
    0.07
    uff
    0.07
    363
    0.06
    dash
    0.06
    iff
    0.06
     door
    0.06
    -room
    0.06
    avez
    0.06
    dge
    0.06
    Activations Density 0.002%

    No Known Activations