© 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 EvalsExportsinterp-engineNEWAPI 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. 1825
    Prev
    Next
    INDEX
    Explanations

    instances of the word "This" and related references signaling an event or activity

    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
     various
    -0.06
    rote
    -0.06
     Gala
    -0.06
     other
    -0.05
     as
    -0.05
     [
    -0.05
     Asian
    -0.05
     arr
    -0.05
     catalogue
    -0.05
    591
    -0.05
    POSITIVE LOGITS
     Glas
    0.07
    ì¹
    0.07
     evet
    0.07
    .Metro
    0.07
    epad
    0.07
    å´İ
    0.07
    ÑĢÑĥд
    0.07
    .gt
    0.07
    linger
    0.07
    illac
    0.07
    Activations Density 0.018%

    No Known Activations