© 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. 95971
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright, licensing, and public access

    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
    id
    -0.06
    jiang
    -0.06
     Saga
    -0.06
    idian
    -0.06
     AS
    -0.06
     Memories
    -0.06
    348
    -0.05
    let
    -0.05
     companions
    -0.05
    .
    -0.05
    POSITIVE LOGITS
    /GPL
    0.10
    /copyleft
    0.09
    glich
    0.09
    evice
    0.08
    AYER
    0.08
    /open
    0.08
     lược
    0.08
    avou
    0.08
    /free
    0.08
    UPER
    0.07
    Activations Density 0.001%

    No Known Activations