© 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. 18728
    Prev
    Next
    INDEX
    Explanations

    URLs or paths related to code repositories and their documentation

    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
    iken
    -0.07
    ÑģÑĥ
    -0.07
    bum
    -0.07
    ovo
    -0.07
     maduras
    -0.07
    ÇIJ
    -0.07
    شت
    -0.07
     noveller
    -0.06
     tetas
    -0.06
    _HANDLE
    -0.06
    POSITIVE LOGITS
    /master
    0.09
     branch
    0.08
    /latest
    0.07
    /main
    0.07
     Branch
    0.07
    HEAD
    0.07
     main
    0.07
     commit
    0.07
     master
    0.06
     latest
    0.06
    Activations Density 0.001%

    No Known Activations