© 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. 15-LLAMASCOPE-RES-131K
    11. 26704
    Prev
    Next
    INDEX
    Explanations

    information about theater showtimes and locations

    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
    akte
    -0.06
    ansi
    -0.06
    bed
    -0.06
     agency
    -0.06
    eldom
    -0.06
    586
    -0.06
     Celt
    -0.06
    indr
    -0.05
     Rolls
    -0.05
     Fund
    -0.05
    POSITIVE LOGITS
    WithValue
    0.07
    PRI
    0.07
    .codes
    0.07
     comfy
    0.07
    fy
    0.07
    anut
    0.07
    ÑĤаж
    0.07
     chiếu
    0.06
    dül
    0.06
    urat
    0.06
    Activations Density 0.003%

    No Known Activations