© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106802
    Prev
    Next
    INDEX
    Explanations

    phrases related to horse racing competition and analysis

    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
     bund
    -0.07
    æ°
    -0.07
    _skin
    -0.07
     -*-č↵
    -0.07
    ucene
    -0.07
    pag
    -0.07
    rottle
    -0.07
    анÑĸÑı
    -0.06
    #ac
    -0.06
    ovnÃŃ
    -0.06
    POSITIVE LOGITS
     horses
    0.09
     horse
    0.08
     trainer
    0.08
    idar
    0.07
     geld
    0.07
     trainers
    0.07
     Racing
    0.07
     stakes
    0.07
     Trainer
    0.07
     rac
    0.06
    Activations Density 0.052%

    No Known Activations