© 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. 15-LLAMASCOPE-RES-131K
    11. 85975
    Prev
    Next
    INDEX
    Explanations

    numerical values or expressions

    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
     stil
    -0.06
     Kir
    -0.06
    İ
    -0.06
    lems
    -0.06
    ulers
    -0.06
     Como
    -0.06
    ãĥĨãĥ«
    -0.06
     Renders
    -0.06
    ocols
    -0.05
     Jarvis
    -0.05
    POSITIVE LOGITS
    arer
    0.07
    ãĤŃãĥ¥
    0.07
    elman
    0.07
    rych
    0.07
    CLUD
    0.07
     erm
    0.07
    PPER
    0.06
    Æ°Æ¡
    0.06
    /epl
    0.06
    trak
    0.06
    Activations Density 0.032%

    No Known Activations