© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41282
    Prev
    Next
    INDEX
    Explanations

    references to news reporting and media sources

    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
     skins
    -0.06
    arts
    -0.06
    nette
    -0.06
    pio
    -0.06
     anc
    -0.06
     Harr
    -0.06
    iley
    -0.06
    attern
    -0.05
    ais
    -0.05
    ays
    -0.05
    POSITIVE LOGITS
    562
    0.07
    dech
    0.07
    stants
    0.07
     vidé
    0.07
    agraph
    0.07
    Å¡ti
    0.07
    isma
    0.07
    paren
    0.07
    NullOr
    0.06
     semiclass
    0.06
    Activations Density 0.008%

    No Known Activations