© 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. 96135
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and items related to home improvement or decor

    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
    .scalablytyped
    -0.07
    %C
    -0.07
    -loader
    -0.07
    664
    -0.07
    388
    -0.07
    997
    -0.07
    [email
    -0.07
    [s
    -0.07
    inder
    -0.07
     Hüs
    -0.06
    POSITIVE LOGITS
     â
    0.08
    â
    0.08
    apos
    0.07
    istrovstvÃŃ
    0.07
     best
    0.07
     Feinstein
    0.06
     flush
    0.06
     shut
    0.06
     super
    0.06
    ylim
    0.06
    Activations Density 0.002%

    No Known Activations