© 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. 83539
    Prev
    Next
    INDEX
    Explanations

    aspects of fashion and clothing descriptions

    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
    409
    -0.07
    Ñıн
    -0.07
    -decoration
    -0.07
    inqu
    -0.06
    aph
    -0.06
    387
    -0.06
    fbe
    -0.06
    rough
    -0.06
    ewood
    -0.06
     zby
    -0.06
    POSITIVE LOGITS
    ä¸Ī
    0.09
    midi
    0.08
     midi
    0.07
    opis
    0.06
    ilim
    0.06
    ceptors
    0.06
    rei
    0.06
    รส
    0.06
    /DD
    0.06
     stretch
    0.06
    Activations Density 0.013%

    No Known Activations