© 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. 4477
    Prev
    Next
    INDEX
    Explanations

    references to copyright laws and fair use principles

    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
    atham
    -0.06
    ÄĽ
    -0.05
    eting
    -0.05
    -uppercase
    -0.05
     double
    -0.05
     Siri
    -0.05
     ob
    -0.05
     add
    -0.05
    eren
    -0.05
     Minority
    -0.05
    POSITIVE LOGITS
     nackte
    0.09
    Fair
    0.08
    /epl
    0.08
    ODULE
    0.07
    ìļ´ëį°
    0.07
    ãĤ¤ãĤº
    0.07
     ört
    0.07
     Fair
    0.07
    claimer
    0.07
    .Restr
    0.07
    Activations Density 0.006%

    No Known Activations