© 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. 90870
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring and judging in boxing matches

    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
    eyse
    -0.08
    ninger
    -0.07
     Watkins
    -0.07
    entine
    -0.06
    úi
    -0.06
    ®¤
    -0.06
    aign
    -0.06
    jÃŃ
    -0.06
    ierz
    -0.06
    ůj
    -0.06
    POSITIVE LOGITS
    اÙĨس
    0.06
     Deg
    0.06
    åĪ¤
    0.06
    rap
    0.06
    Deg
    0.06
    gii
    0.06
     aggression
    0.06
    Apis
    0.06
    оглаÑģ
    0.06
    ApiClient
    0.06
    Activations Density 0.001%

    No Known Activations