© 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. 5908
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or metrics

    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
     Eden
    -0.07
     tit
    -0.07
    allen
    -0.06
    ека
    -0.06
    inst
    -0.06
    ichtig
    -0.06
     Rin
    -0.06
    è¾
    -0.06
    ynes
    -0.06
     fin
    -0.05
    POSITIVE LOGITS
    uhl
    0.07
    ienne
    0.06
    Profiler
    0.06
    jc
    0.06
    PMENT
    0.06
    acey
    0.06
    çݯ
    0.06
     sequences
    0.06
    roller
    0.06
    رÙĪÛĮ
    0.06
    Activations Density 0.004%

    No Known Activations