Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44125
    Prev
    Next
    INDEX
    Explanations

    types of artistic and psychological concepts

    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
    enville
    -0.07
    leigh
    -0.06
    WARE
    -0.06
    boa
    -0.06
    rega
    -0.06
    antiago
    -0.06
    AllWindows
    -0.06
    å¹
    -0.06
    upertino
    -0.06
    iyat
    -0.06
    POSITIVE LOGITS
    ically
    0.14
    yped
    0.12
    ype
    0.12
    al
    0.12
    ic
    0.11
    ypes
    0.11
    ypical
    0.10
    ical
    0.10
    etypes
    0.10
    YPE
    0.09
    Activations Density 0.002%

    No Known Activations