© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119990
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structures used in software development

    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
    .updateDynamic
    -0.07
    ãĥ©ãĥĥãĤ¯
    -0.07
     Santana
    -0.06
    ãĥ¼ãĤ¹
    -0.06
     kâ
    -0.06
    let
    -0.06
     Warn
    -0.06
     desar
    -0.06
    utf
    -0.06
    uka
    -0.06
    POSITIVE LOGITS
     underlying
    0.07
    ITHER
    0.07
     get
    0.07
    cul
    0.06
     lấy
    0.06
    asca
    0.06
    auer
    0.06
    Ñıн
    0.06
    asmine
    0.06
    oubles
    0.06
    Activations Density 0.009%

    No Known Activations