© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    strong recommendations and expressions of intent related to books

    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
    #ad
    -0.07
     defaultManager
    -0.07
    veau
    -0.07
    tics
    -0.06
    Reuse
    -0.06
     ÑĤабли
    -0.06
    Reusable
    -0.06
     Rek
    -0.06
    erne
    -0.06
     Aad
    -0.06
    POSITIVE LOGITS
     popcorn
    0.07
    branches
    0.06
    atron
    0.06
     doma
    0.06
     flock
    0.06
    igon
    0.06
     watch
    0.06
     purchase
    0.06
    zc
    0.06
    net
    0.06
    Activations Density 0.032%

    No Known Activations