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. 43750
    Prev
    Next
    INDEX
    Explanations

    words related to atheism and its discussion in various contexts

    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
    antino
    -0.07
    avec
    -0.06
    avo
    -0.06
    aje
    -0.06
    ůl
    -0.06
     Jess
    -0.06
    ecz
    -0.06
    ساÙĨÛĮ
    -0.06
    avl
    -0.06
    atori
    -0.06
    POSITIVE LOGITS
    letic
    0.14
    letes
    0.14
    istic
    0.13
    istical
    0.13
    ists
    0.12
    oretical
    0.12
    letics
    0.12
    ism
    0.12
    istically
    0.11
    ological
    0.11
    Activations Density 0.003%

    No Known Activations