© 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. 85509
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and their contents in the text

    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
    ë¶ĢíĦ°
    -0.07
    ãĥªãĤ¢
    -0.07
    STITUTE
    -0.07
    auss
    -0.06
    ëį°
    -0.06
    ambda
    -0.06
    æĹ
    -0.06
    DonaldTrump
    -0.06
    mÃŃ
    -0.06
    &type
    -0.06
    POSITIVE LOGITS
     chief
    0.08
     such
    0.08
     напÑĢимеÑĢ
    0.07
     like
    0.07
    ï¼Įæ¯Ķ
    0.07
     napÅĻ
    0.07
     napÅĻÃŃklad
    0.07
    ä¾ĭå¦Ĥ
    0.07
     ÐĿапÑĢимеÑĢ
    0.07
     Examples
    0.07
    Activations Density 0.021%

    No Known Activations