© 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. 14205
    Prev
    Next
    INDEX
    Explanations

    references to literary works and authors

    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
    vf
    -0.06
    ilon
    -0.06
    ientes
    -0.06
    asar
    -0.06
     Whit
    -0.06
    atted
    -0.06
    yster
    -0.06
    landa
    -0.06
    hel
    -0.06
     götür
    -0.06
    POSITIVE LOGITS
    /screen
    0.06
    orno
    0.06
    书
    0.06
    SER
    0.06
    lob
    0.06
    @author
    0.06
     AUTHOR
    0.06
     bdsm
    0.06
    -writing
    0.06
    à¹Ģà¸ĭà¸Ńร
    0.06
    Activations Density 0.007%

    No Known Activations