© 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. 108860
    Prev
    Next
    INDEX
    Explanations

    timestamps and date-related information

    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
    acon
    -0.07
     earliest
    -0.06
     A
    -0.06
    ,
    -0.06
    ieur
    -0.06
     no
    -0.06
    .
    -0.06
     Panc
    -0.06
     No
    -0.06
     a
    -0.06
    POSITIVE LOGITS
    _bag
    0.08
    UILTIN
    0.08
    presso
    0.07
     ÑĥÑģ
    0.07
    .lot
    0.07
    .scalablytyped
    0.07
    ä¸Ī
    0.07
     pás
    0.07
    .jd
    0.07
    istrovstvÃŃ
    0.07
    Activations Density 0.001%

    No Known Activations