© 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 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. 78372
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performance

    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
    oven
    -0.07
    spor
    -0.07
     needle
    -0.07
     Needle
    -0.07
    urovision
    -0.07
    antar
    -0.06
    plevel
    -0.06
    adu
    -0.06
    ORIZONTAL
    -0.06
     anlay
    -0.06
    POSITIVE LOGITS
    aison
    0.07
    asca
    0.06
     bun
    0.06
    ymes
    0.06
    Cro
    0.06
    482
    0.06
     Carlton
    0.06
    season
    0.06
     seasonal
    0.06
     Cro
    0.06
    Activations Density 0.018%

    No Known Activations