© 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. 17-LLAMASCOPE-RES-131K
    11. 28259
    Prev
    Next
    INDEX
    Explanations

    terms related to NFL draft picks and player evaluations

    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
    pta
    -0.07
    uhn
    -0.07
    brero
    -0.06
    atee
    -0.06
     Ware
    -0.06
    erd
    -0.06
    utzt
    -0.06
    inç
    -0.06
    Ware
    -0.06
    åĬłå·¥
    -0.06
    POSITIVE LOGITS
    mov
    0.07
    utenberg
    0.06
     Gew
    0.06
    cznie
    0.06
    ianne
    0.06
    -owned
    0.06
    opot
    0.06
    üst
    0.06
     owned
    0.06
    SED
    0.06
    Activations Density 0.005%

    No Known Activations