© 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. 31724
    Prev
    Next
    INDEX
    Explanations

    affirmations or descriptors of products or services

    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
     mechanically
    -0.07
     Pul
    -0.06
     spl
    -0.06
    umhur
    -0.06
     Technique
    -0.06
     tidal
    -0.06
     unary
    -0.06
     Mechanical
    -0.06
     trend
    -0.05
    aura
    -0.05
    POSITIVE LOGITS
    λλη
    0.08
    zion
    0.08
    VERS
    0.07
    aklı
    0.07
    sÃŃ
    0.07
    ģn
    0.07
    ä¸Ī夫
    0.07
    versible
    0.07
    eno
    0.07
    vens
    0.07
    Activations Density 0.021%

    No Known Activations