© 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. 22-LLAMASCOPE-RES-131K
    11. 3685
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and outcomes

    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
     fich
    -0.07
    uce
    -0.07
     bergen
    -0.06
    HR
    -0.06
    /plugin
    -0.06
    zeigen
    -0.06
     oppon
    -0.06
    612
    -0.06
    datatable
    -0.06
    hod
    -0.06
    POSITIVE LOGITS
     overtime
    0.09
     their
    0.08
     round
    0.07
     Tick
    0.07
     Round
    0.07
    _ticks
    0.07
     penalties
    0.07
     ticking
    0.07
    AME
    0.07
    Ticks
    0.07
    Activations Density 0.018%

    No Known Activations