© 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. 127231
    Prev
    Next
    INDEX
    Explanations

    code or syntax related to object-oriented programming

    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
    REM
    -0.07
     dean
    -0.06
    eyh
    -0.06
    tiv
    -0.06
    brief
    -0.06
    structor
    -0.06
    ãģĭãĤı
    -0.06
    reach
    -0.06
    ại
    -0.06
    prt
    -0.06
    POSITIVE LOGITS
    htub
    0.07
    ONTAL
    0.07
    RAINT
    0.06
    flater
    0.06
    metic
    0.06
    ored
    0.06
    mer
    0.06
    меÑĢ
    0.06
    ackets
    0.06
    ButtonType
    0.06
    Activations Density 0.005%

    No Known Activations