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. 43598
    Prev
    Next
    INDEX
    Explanations

    references to colors or descriptors associated with individuals

    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
    chers
    -0.07
    AffineTransform
    -0.06
    VERAGE
    -0.06
    ¶ļ
    -0.06
    noop
    -0.06
    ä¼į
    -0.06
    activex
    -0.06
    edo
    -0.06
    DDevice
    -0.06
    .sa
    -0.06
    POSITIVE LOGITS
    orgeous
    0.12
    odd
    0.12
    lam
    0.11
    inger
    0.11
    ingers
    0.11
    lor
    0.10
    rett
    0.10
    INGER
    0.10
    ypsy
    0.10
    wen
    0.09
    Activations Density 0.007%

    No Known Activations