© 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. 78012
    Prev
    Next
    INDEX
    Explanations

    references to football players and their statistics

    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
    ut
    -0.07
    aised
    -0.06
    ibrary
    -0.06
    ãĥĸãĥŃ
    -0.06
    orld
    -0.06
     participant
    -0.06
    Veter
    -0.06
     Mojo
    -0.06
    igid
    -0.06
    olas
    -0.06
    POSITIVE LOGITS
     Prime
    0.06
    ahlen
    0.06
    idla
    0.06
    æĻ´
    0.06
    nic
    0.06
    ynos
    0.06
    /Dk
    0.06
    COLUMN
    0.06
    raison
    0.06
    æIJ¬
    0.06
    Activations Density 0.021%

    No Known Activations