© 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. 91680
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data handling

    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
     Clipboard
    -0.07
    leans
    -0.07
     toggle
    -0.07
    avit
    -0.07
     clipboard
    -0.07
    clipboard
    -0.07
    iphy
    -0.07
    TabPage
    -0.07
    -checkbox
    -0.06
     hook
    -0.06
    POSITIVE LOGITS
    select
    0.09
     selects
    0.09
     select
    0.09
     selections
    0.08
     selection
    0.08
     sele
    0.08
    <select
    0.08
     choices
    0.08
    Select
    0.08
     dro
    0.08
    Activations Density 0.015%

    No Known Activations