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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103182
    Prev
    Next
    INDEX
    Explanations

    actions or movements of characters in a narrative

    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
     zag
    -0.07
     ours
    -0.06
    oram
    -0.06
    amo
    -0.06
    bett
    -0.06
    tual
    -0.06
    aspers
    -0.06
    orro
    -0.06
    #ad
    -0.06
    iais
    -0.06
    POSITIVE LOGITS
     itemprop
    0.07
    ickerView
    0.07
    ellular
    0.07
    ávÄĽ
    0.07
    584
    0.07
    eler
    0.07
    -prepend
    0.06
    _CF
    0.06
    úsqueda
    0.06
    -navbar
    0.06
    Activations Density 0.023%

    No Known Activations