© 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. 18714
    Prev
    Next
    INDEX
    Explanations

    references to CPU performance and specifications

    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
    bies
    -0.07
    edy
    -0.07
    keh
    -0.07
    ese
    -0.07
     ÑĩаÑģÑĤ
    -0.07
    ør
    -0.07
    bern
    -0.07
    ileo
    -0.07
    ewart
    -0.06
    ams
    -0.06
    POSITIVE LOGITS
    ÑĩаÑĶ
    0.07
    ulp
    0.07
    730
    0.07
     endors
    0.06
    илÑı
    0.06
    онÑĮ
    0.06
    ISIBLE
    0.06
    ova
    0.06
     Haus
    0.06
    venile
    0.06
    Activations Density 0.010%

    No Known Activations