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. 43892
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and materials

    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
    icana
    -0.06
    ypress
    -0.06
    lander
    -0.06
     Ñģел
    -0.06
    bcd
    -0.06
    ано
    -0.06
    ÑĻ
    -0.06
     Mason
    -0.06
    ano
    -0.06
     bro
    -0.06
    POSITIVE LOGITS
    hal
    0.12
    h
    0.11
    pus
    0.11
    vá
    0.11
    sz
    0.10
    utas
    0.10
    halt
    0.10
    ny
    0.09
    tem
    0.09
    kö
    0.09
    Activations Density 0.001%

    No Known Activations