© 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. 29265
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a beginning or initiation of an event or action

    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
    ellular
    -0.07
    ories
    -0.06
    zcze
    -0.06
    chine
    -0.06
    át
    -0.06
    allest
    -0.06
    htub
    -0.06
    ahan
    -0.06
    orks
    -0.06
    ocale
    -0.06
    POSITIVE LOGITS
    ÙĦس
    0.08
    activex
    0.07
    gers
    0.07
    piler
    0.07
     innoc
    0.07
    icum
    0.07
    /down
    0.06
     careers
    0.06
     siendo
    0.06
    nings
    0.06
    Activations Density 0.004%

    No Known Activations