© 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. 42804
    Prev
    Next
    INDEX
    Explanations

    references to web links or URLs

    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
    urtle
    -0.07
    enburg
    -0.07
    ikes
    -0.07
    ramid
    -0.07
    ú
    -0.06
    iesz
    -0.06
    é½
    -0.06
    ove
    -0.06
    hil
    -0.06
    hton
    -0.06
    POSITIVE LOGITS
    shal
    0.07
    359
    0.07
    Evt
    0.06
    aje
    0.06
    elik
    0.06
     periodic
    0.06
     el
    0.06
     ThÆ°á»Ŀng
    0.06
    .MATCH
    0.05
    ảy
    0.05
    Activations Density 0.000%

    No Known Activations