© 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. 53980
    Prev
    Next
    INDEX
    Explanations

    textual elements related to citation or reference formatting

    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
    elay
    -0.06
    thon
    -0.06
    SEL
    -0.05
    otted
    -0.05
     Late
    -0.05
    ohn
    -0.05
    getitem
    -0.05
     wing
    -0.05
    roup
    -0.05
    late
    -0.05
    POSITIVE LOGITS
    ritis
    0.07
    visor
    0.07
    orca
    0.07
    /gin
    0.06
    istes
    0.06
    ä½ľ
    0.06
    wins
    0.06
    .Cmd
    0.06
    ¿IJ
    0.06
     célib
    0.06
    Activations Density 0.020%

    No Known Activations