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. 43578
    Prev
    Next
    INDEX
    Explanations

    references to "Hill" in various contexts, particularly related to awards or honors

    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
    lei
    -0.08
    ukt
    -0.07
    sı
    -0.07
    ÙĴ
    -0.07
    s
    -0.07
    ligne
    -0.07
    .struts
    -0.07
    udent
    -0.07
    ecz
    -0.07
    utch
    -0.07
    POSITIVE LOGITS
    iard
    0.15
    iker
    0.12
    iards
    0.11
    endale
    0.10
    erman
    0.10
    Billy
    0.10
    crest
    0.10
    er
    0.10
    ermann
    0.10
    house
    0.09
    Activations Density 0.008%

    No Known Activations