© 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. 18625
    Prev
    Next
    INDEX
    Explanations

    numerals and statistics related to demographic and electoral data

    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
    .§
    -0.08
     nues
    -0.08
    .DropDown
    -0.07
     poil
    -0.07
    .instrument
    -0.07
    .intent
    -0.07
    âu
    -0.07
     polis
    -0.07
    виÑĩ
    -0.07
    ÑģилÑĮ
    -0.07
    POSITIVE LOGITS
    /Foundation
    0.07
     thousands
    0.07
    RYPTO
    0.06
    salt
    0.06
     Thousands
    0.06
    unken
    0.06
     hundreds
    0.06
    Alive
    0.06
    -urlencoded
    0.06
    rsa
    0.06
    Activations Density 0.049%

    No Known Activations