© 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. 80796
    Prev
    Next
    INDEX
    Explanations

    references to Broadway

    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
    tery
    -0.06
     ChÃŃ
    -0.06
    tings
    -0.06
    s
    -0.06
    aml
    -0.06
    BERS
    -0.06
    /fa
    -0.06
    iest
    -0.06
    eral
    -0.06
    ãĥĨãĥ«
    -0.06
    POSITIVE LOGITS
    hesive
    0.09
    nun
    0.07
    nan
    0.07
    band
    0.07
    hurst
    0.07
    ripple
    0.07
    wy
    0.07
    leaf
    0.07
    lier
    0.07
    pread
    0.07
    Activations Density 0.007%

    No Known Activations