© 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. 84194
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and underscores 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
    eç
    -0.07
    holm
    -0.07
    Kay
    -0.07
    xampp
    -0.07
    ensa
    -0.07
    eyse
    -0.07
    ripper
    -0.07
    æĹıèĩªæ²»
    -0.07
    jwt
    -0.06
    ãĤ«ãĥ«
    -0.06
    POSITIVE LOGITS
     =
    0.07
    99
    0.06
    983
    0.06
    /=
    0.06
    tem
    0.06
     _)
    0.06
    nbsp
    0.06
     //=
    0.06
     McCarthy
    0.06
     _,
    0.06
    Activations Density 0.022%

    No Known Activations