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. 43827
    Prev
    Next
    INDEX
    Explanations

    references to apparel and fashion items

    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
    _GB
    -0.07
    βα
    -0.07
    ajar
    -0.06
    ãĥ¼ãĥĨ
    -0.06
    koa
    -0.06
    forman
    -0.06
    ÙİØ£
    -0.06
    ponsible
    -0.06
    عÙĩ
    -0.06
    bows
    -0.06
    POSITIVE LOGITS
     equivalent
    0.20
     corresponding
    0.19
     reminiscent
    0.17
     resembling
    0.17
     akin
    0.17
     comparable
    0.15
     similar
    0.14
     Equivalent
    0.14
     together
    0.13
    akin
    0.13
    Activations Density 0.008%

    No Known Activations