© 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. 57326
    Prev
    Next
    INDEX
    Explanations

    references to inductions into various halls of fame

    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
    acket
    -0.09
    twig
    -0.08
    urf
    -0.08
    ãĤ¤ãĤ¯
    -0.07
    ÑĪов
    -0.07
    arf
    -0.07
    Unused
    -0.07
    ìĩ
    -0.07
    ÑĢади
    -0.07
    Äĥm
    -0.07
    POSITIVE LOGITS
     into
    0.08
     hall
    0.08
     Hall
    0.08
     halls
    0.07
    hall
    0.07
    608
    0.06
    into
    0.06
    Hall
    0.06
     permanent
    0.06
    405
    0.06
    Activations Density 0.005%

    No Known Activations