© 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. 15-LLAMASCOPE-RES-131K
    11. 1513
    Prev
    Next
    INDEX
    Explanations

    references to winning and losing in sports contexts

    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
    473
    -0.09
    sez
    -0.07
    au
    -0.06
    254
    -0.06
    jourd
    -0.06
    _maker
    -0.06
    ·»
    -0.06
    زش
    -0.06
    funcs
    -0.06
     gol
    -0.06
    POSITIVE LOGITS
    ixa
    0.08
    iry
    0.07
    ilty
    0.07
    omentum
    0.07
     Weinstein
    0.06
     æ¶
    0.06
    ypy
    0.06
    illance
    0.06
    itre
    0.06
    AccessType
    0.06
    Activations Density 0.002%

    No Known Activations