© 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. 69035
    Prev
    Next
    INDEX
    Explanations

    titles of movies or film references

    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
    istan
    -0.07
     abstract
    -0.06
     JetBrains
    -0.06
    iseum
    -0.06
    362
    -0.06
    åħIJ
    -0.06
    fila
    -0.06
    rens
    -0.06
    iola
    -0.06
     mounting
    -0.06
    POSITIVE LOGITS
    assen
    0.08
    198
    0.08
     Hover
    0.07
    kowski
    0.07
     hover
    0.07
    ÄĽj
    0.07
     Bucks
    0.07
    ÃŁ
    0.07
    xl
    0.06
    ahl
    0.06
    Activations Density 0.002%

    No Known Activations