© 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. 30279
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    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
     nors
    -0.08
    uchs
    -0.08
    elage
    -0.07
    linkplain
    -0.07
    moth
    -0.07
    stry
    -0.07
    Stretch
    -0.06
    ewan
    -0.06
    oire
    -0.06
    elmet
    -0.06
    POSITIVE LOGITS
    apiro
    0.06
    ernet
    0.06
    ogr
    0.06
    inski
    0.06
     Zug
    0.06
    [js
    0.06
     Pascal
    0.06
    _Generic
    0.05
     Eu
    0.05
     Shall
    0.05
    Activations Density 0.021%

    No Known Activations