© 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. 9-LLAMASCOPE-RES-131K
    11. 98884
    Prev
    Next
    INDEX
    Explanations

    references to specific events or occurrences related to sports outcomes and 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
     tub
    -0.07
     die
    -0.06
     bar
    -0.06
     that
    -0.06
     capsule
    -0.06
     Clar
    -0.06
     clar
    -0.06
     wy
    -0.06
     variable
    -0.06
     Die
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĹ
    0.08
    ivec
    0.08
    assin
    0.07
    æµħ
    0.07
    _Msk
    0.07
    amarin
    0.07
     اختÙĦ
    0.07
    å¹²
    0.07
    .ud
    0.07
    Peripheral
    0.07
    Activations Density 0.012%

    No Known Activations