© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62683
    Prev
    Next
    INDEX
    Explanations

    digital document links or references

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Parad
    -0.08
    æı®
    -0.07
    ãĥĥãĤ°
    -0.06
     ditch
    -0.06
    ë¹Ļ
    -0.06
    .DAL
    -0.06
    thead
    -0.06
    ги
    -0.06
    ouns
    -0.06
     Imper
    -0.06
    POSITIVE LOGITS
    amas
    0.06
    .Te
    0.06
    olang
    0.06
    orman
    0.06
    .pin
    0.06
    lags
    0.06
    EFA
    0.06
    ADIUS
    0.06
     Vernon
    0.06
    lops
    0.06
    Activations Density 0.001%

    No Known Activations