© 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. 107279
    Prev
    Next
    INDEX
    Explanations

    specific data manipulation commands or operations related to data structures

    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
     же
    -0.08
    leigh
    -0.07
    olt
    -0.07
    baÅŁ
    -0.07
    jie
    -0.07
    allah
    -0.07
    OOM
    -0.07
    elsey
    -0.07
    fen
    -0.07
    alom
    -0.07
    POSITIVE LOGITS
    anguages
    0.07
       
    0.07
    arend
    0.06
    ÑĢÑı
    0.06
    .getLine
    0.06
    ameda
    0.06
    ocate
    0.06
    quot
    0.06
    ;element
    0.06
    إ
    0.06
    Activations Density 0.002%

    No Known Activations