© 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 EvalsExportsAPI 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. 57363
    Prev
    Next
    INDEX
    Explanations

    commands and references related to software installation and configuration

    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
    serter
    -0.07
    engeance
    -0.07
    ActionCreators
    -0.07
    isku
    -0.07
     sát
    -0.07
    ifle
    -0.07
     serialVersionUID
    -0.07
    ergus
    -0.07
    cade
    -0.07
    esis
    -0.07
    POSITIVE LOGITS
    /releases
    0.06
     bull
    0.06
    (optional
    0.06
    inine
    0.06
     purchased
    0.05
     th
    0.05
     Amazon
    0.05
    .eth
    0.05
     Hayward
    0.05
     Bull
    0.05
    Activations Density 0.001%

    No Known Activations