© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125548
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and project management

    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
    .gstatic
    -0.07
    stile
    -0.07
    ede
    -0.06
    uteur
    -0.06
    assa
    -0.06
    unes
    -0.06
    enant
    -0.06
    issy
    -0.06
    asma
    -0.06
    299
    -0.06
    POSITIVE LOGITS
    erap
    0.07
    tach
    0.07
    oleon
    0.06
    нок
    0.06
    ouser
    0.06
    Ñīин
    0.06
    _inactive
    0.06
     Mature
    0.06
     [~,
    0.06
     |[
    0.06
    Activations Density 0.002%

    No Known Activations