© 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. 73981
    Prev
    Next
    INDEX
    Explanations

    numerical values or scores related to sports events

    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
     extents
    -0.07
    jte
    -0.07
    uzzi
    -0.07
    664
    -0.07
    forge
    -0.07
    ANDOM
    -0.07
     COPYRIGHT
    -0.06
    zi
    -0.06
    _TESTS
    -0.06
    lý
    -0.06
    POSITIVE LOGITS
    anta
    0.06
    eto
    0.06
    âĢĮâĢĮ
    0.06
    yon
    0.06
    ½æķ°
    0.06
    ijkl
    0.06
     score
    0.06
    ragon
    0.06
    arie
    0.06
    tsky
    0.05
    Activations Density 0.001%

    No Known Activations