© 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. 5959
    Prev
    Next
    INDEX
    Explanations

    numerical values or rates related to pricing and costs

    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
     (
    -0.07
    reas
    -0.06
     W
    -0.06
     unb
    -0.06
    resent
    -0.06
     [
    -0.06
    Å¡k
    -0.05
    ÂŃs
    -0.05
     unre
    -0.05
    ller
    -0.05
    POSITIVE LOGITS
    -animate
    0.07
    _PKG
    0.07
    (=)
    0.07
    ãĥ¼ãĥ¼
    0.07
    prak
    0.07
    uppen
    0.07
    Clone
    0.07
    лÑĸÑĤ
    0.07
    __.__
    0.06
    ioso
    0.06
    Activations Density 0.000%

    No Known Activations