© 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. 17-LLAMASCOPE-RES-131K
    11. 75468
    Prev
    Next
    INDEX
    Explanations

    historical figures and their accomplishments

    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
    actionDate
    -0.10
    istrovstvÃŃ
    -0.10
    DCALL
    -0.10
    _marshall
    -0.10
    isclosed
    -0.10
    ofilm
    -0.09
    efon
    -0.09
     subur
    -0.09
    ardu
    -0.09
    .scalablytyped
    -0.09
    POSITIVE LOGITS
    le
    0.08
    [
    0.07
    ↵
    0.06
     without
    0.06
     i
    0.06
    ...
    0.06
     pole
    0.06
     as
    0.06
     higher
    0.06
     liv
    0.06
    Activations Density 0.004%

    No Known Activations