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. 5663
    Prev
    Next
    INDEX
    Explanations

    specific names or references to people and their actions

    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
    anean
    -0.07
    amarin
    -0.06
    ibi
    -0.06
    วล
    -0.06
    ìĿ´ëĵľ
    -0.06
    ocop
    -0.06
    apia
    -0.06
     ض
    -0.06
    Sdk
    -0.06
    merce
    -0.06
    POSITIVE LOGITS
    .Sm
    0.08
     sm
    0.08
    /sm
    0.07
    (sm
    0.07
     Sm
    0.07
    inton
    0.07
    sonian
    0.06
    thur
    0.06
    ÅĻenÃŃ
    0.06
    اÙĪÙĬ
    0.06
    Activations Density 0.011%

    No Known Activations