© 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. 55225
    Prev
    Next
    INDEX
    Explanations

    references to specific numbers and temporal events, particularly in a racing or statistical 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
    olson
    -0.07
    ิมà¸ŀ
    -0.06
    ÑģÑĤÑİ
    -0.06
    è¼Ķ
    -0.06
     Domino
    -0.06
    PÅĻi
    -0.06
     Gee
    -0.06
     Xxx
    -0.06
    ÑĸÑĶ
    -0.06
     Gerr
    -0.06
    POSITIVE LOGITS
    -by
    0.08
    rames
    0.07
    ãĥ¬ãĥ¼
    0.07
    sto
    0.07
    hat
    0.07
    anship
    0.06
    casting
    0.06
    ëĭ¹
    0.06
    emento
    0.06
    ysics
    0.06
    Activations Density 0.037%

    No Known Activations