© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89845
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    antan
    -0.08
    olini
    -0.08
    ceae
    -0.08
    ilor
    -0.08
    ignet
    -0.08
    ccione
    -0.07
    039
    -0.07
    ÑģÑıÑĤ
    -0.07
    باش
    -0.07
    imonial
    -0.07
    POSITIVE LOGITS
     suddenly
    0.08
     they
    0.07
     began
    0.07
     came
    0.06
     became
    0.06
    3
    0.06
     adher
    0.05
    [
    0.05
    upon
    0.05
     adherence
    0.05
    Activations Density 0.008%

    No Known Activations