© 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. 27497
    Prev
    Next
    INDEX
    Explanations

    references to cybercrime and related academic or encyclopedic content

    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
    è¼Ķ
    -0.08
    abase
    -0.07
    irit
    -0.07
    fir
    -0.07
    &m
    -0.07
    Disallow
    -0.07
    ...↵↵↵↵
    -0.07
    etest
    -0.06
    ãĤ¸ãĤª
    -0.06
    ãĥ©ãĥĥãĤ¯
    -0.06
    POSITIVE LOGITS
    âĢħ
    0.07
    %C
    0.07
    Ù¬
    0.06
    /fa
    0.06
    actionDate
    0.06
    -unstyled
    0.06
    lah
    0.06
     Wikispecies
    0.06
     ÙĦÙĥرة
    0.06
    ifying
    0.06
    Activations Density 0.004%

    No Known Activations