© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4462
    Prev
    Next
    INDEX
    Explanations

    references to home maintenance or repair instructions

    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
     pás
    -0.07
    asts
    -0.06
    bourg
    -0.06
    ipo
    -0.06
    ê¸Ī
    -0.06
     windshield
    -0.06
    ÄĽst
    -0.06
    ewe
    -0.06
     exh
    -0.06
    åĩ¡
    -0.06
    POSITIVE LOGITS
     Water
    0.09
     water
    0.09
    Water
    0.08
    water
    0.07
     WATER
    0.07
    .water
    0.07
     toilet
    0.07
    urnal
    0.07
    uzey
    0.06
    _water
    0.06
    Activations Density 0.000%

    No Known Activations