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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74942
    Prev
    Next
    INDEX
    Explanations

    actions related to physical tasks and the collection of resources

    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
    heure
    -0.07
    utas
    -0.07
     dump
    -0.07
    bak
    -0.07
    olia
    -0.07
     Dump
    -0.07
    velle
    -0.06
    uku
    -0.06
    generation
    -0.06
    ffen
    -0.06
    POSITIVE LOGITS
     handful
    0.07
    grab
    0.07
    ylum
    0.07
     lấy
    0.06
     educ
    0.06
    yme
    0.06
    åºŃ
    0.06
    atr
    0.06
    eral
    0.06
     bay
    0.06
    Activations Density 0.019%

    No Known Activations