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. 22-LLAMASCOPE-RES-131K
    6. 5452
    Prev
    Next
    INDEX
    Explanations

    expressions indicating intensity or emphasis

    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
    nt
    -0.08
    ults
    -0.08
    ding
    -0.08
    pai
    -0.07
    mer
    -0.06
    apan
    -0.06
    &R
    -0.06
    æĩ
    -0.06
    ugin
    -0.06
     kit
    -0.06
    POSITIVE LOGITS
     frankly
    0.08
     possibly
    0.08
    té
    0.08
    -ÑĤаки
    0.08
    ymax
    0.07
     literally
    0.07
    .unregister
    0.07
     Possibly
    0.07
    ven
    0.07
    comings
    0.07
    Activations Density 0.012%

    No Known Activations