© 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. 121501
    Prev
    Next
    INDEX
    Explanations

    references to fax technology and related terminology

    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
    itzer
    -0.06
     Nose
    -0.06
    933
    -0.06
    UNET
    -0.06
    stre
    -0.06
     fate
    -0.06
    s
    -0.06
    år
    -0.06
    erness
    -0.05
    iyah
    -0.05
    POSITIVE LOGITS
    arella
    0.10
    (es
    0.09
    ossible
    0.07
    adoo
    0.07
    ureau
    0.07
    /email
    0.07
    _resume
    0.07
    quer
    0.07
    ette
    0.07
    esModule
    0.07
    Activations Density 0.002%

    No Known Activations