© 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. 39295
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters used in languages or scripts

    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
    .dsl
    -0.06
    ĽĦ
    -0.06
    ebi
    -0.06
     заб
    -0.06
    ierre
    -0.06
    آ
    -0.06
    ieber
    -0.06
    ekler
    -0.06
    ÃĪ
    -0.06
    ylko
    -0.06
    POSITIVE LOGITS
    CharacterSet
    0.07
     [âĢ¦]↵↵
    0.07
    groupon
    0.07
    emailer
    0.06
    alsex
    0.06
    endcode
    0.06
    -wsj
    0.06
    ecko
    0.06
    479
    0.06
    ignKey
    0.06
    Activations Density 0.001%

    No Known Activations