© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    instances of agreement expressed in conversations or discussions

    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
    loth
    -0.07
    rame
    -0.07
    ÐŀÐĿ
    -0.07
    _attached
    -0.07
    룬
    -0.07
    doch
    -0.07
    ương
    -0.07
    á»±
    -0.07
    ỳ
    -0.07
    AMPLE
    -0.07
    POSITIVE LOGITS
    /dis
    0.07
     ÑģпоÑĢ
    0.07
    able
    0.06
     tow
    0.06
    entin
    0.06
     arg
    0.06
     statements
    0.06
     statement
    0.06
    arendra
    0.06
    亮
    0.06
    Activations Density 0.009%

    No Known Activations