© 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. 118794
    Prev
    Next
    INDEX
    Explanations

    information about artistic collaborations and relationships among historical artists

    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
    .scalablytyped
    -0.09
    åŃĺæ¡£
    -0.08
    iesel
    -0.08
    iationException
    -0.07
    iku
    -0.07
    ApplicationBuilder
    -0.07
    urtles
    -0.07
    ÑĶÑĪ
    -0.07
    abis
    -0.07
    uml
    -0.07
    POSITIVE LOGITS
     lut
    0.07
     anonymous
    0.06
     ceiling
    0.06
     fres
    0.06
     Anonymous
    0.06
     Guid
    0.06
    æ´¾
    0.06
     Lucas
    0.06
     painting
    0.06
     pai
    0.06
    Activations Density 0.038%

    No Known Activations