© 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. 121414
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "got" and its variations in different contexts

    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
     toll
    -0.06
    CALE
    -0.06
    hol
    -0.06
    azar
    -0.06
     Bris
    -0.06
    OLL
    -0.06
    aggio
    -0.06
    à¤Ĥत
    -0.06
     kam
    -0.06
    ester
    -0.06
    POSITIVE LOGITS
    leans
    0.07
    @ResponseBody
    0.07
    ÑĨеп
    0.06
    ovit
    0.06
    iate
    0.06
    \OptionsResolver
    0.06
    bcm
    0.06
     backed
    0.06
    -With
    0.06
    linger
    0.06
    Activations Density 0.017%

    No Known Activations