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. 43634
    Prev
    Next
    INDEX
    Explanations

    references to anatomical terms or structures related to the ulna

    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
    ely
    -0.07
    ey
    -0.07
    adden
    -0.06
     Gord
    -0.06
     Jord
    -0.06
    lung
    -0.06
    iele
    -0.06
    aland
    -0.06
    eh
    -0.06
     åŀ
    -0.06
    POSITIVE LOGITS
    cers
    0.16
    terior
    0.09
    tras
    0.08
    ve
    0.08
    nar
    0.08
    kus
    0.08
    pers
    0.08
    ptic
    0.08
    sert
    0.08
    ser
    0.08
    Activations Density 0.003%

    No Known Activations