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. 43883
    Prev
    Next
    INDEX
    Explanations

    discussions about self-doubt and its impact on 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
    ingly
    -0.07
    alerts
    -0.07
    GOR
    -0.06
    PELL
    -0.06
    lev
    -0.06
    ê²½
    -0.06
    -transitional
    -0.06
    ATO
    -0.06
    latex
    -0.06
    DataBase
    -0.06
    POSITIVE LOGITS
    oub
    0.17
    etermination
    0.12
    estruction
    0.11
    estruct
    0.11
    isc
    0.10
    istr
    0.10
    ign
    0.10
    etest
    0.10
    iss
    0.10
    ram
    0.09
    Activations Density 0.004%

    No Known Activations