© 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. 15-LLAMASCOPE-RES-131K
    11. 87042
    Prev
    Next
    INDEX
    Explanations

    instances of specific names or references in scientific literature

    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
     press
    -0.06
    kami
    -0.06
     fame
    -0.06
    tte
    -0.06
    PathComponent
    -0.06
     e
    -0.05
    foundation
    -0.05
    aÅŁ
    -0.05
    ANGED
    -0.05
     esp
    -0.05
    POSITIVE LOGITS
    .AutoSizeMode
    0.07
     EntityState
    0.07
    ige
    0.07
    izzer
    0.07
    ربÛĮ
    0.07
    isa
    0.07
    سÙĪب
    0.07
    iler
    0.07
    using
    0.06
    icom
    0.06
    Activations Density 0.003%

    No Known Activations