© 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. 3293
    Prev
    Next
    INDEX
    Explanations

    references to horse racing odds 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
    ù
    -0.06
    .TestTools
    -0.06
     каÑĢÑĤи
    -0.06
    abase
    -0.06
    erry
    -0.06
    -dev
    -0.05
    roach
    -0.05
    gran
    -0.05
    mond
    -0.05
     Trang
    -0.05
    POSITIVE LOGITS
     odds
    0.08
    emma
    0.07
    $MESS
    0.07
    .MixedReality
    0.07
    eton
    0.07
    Ø·ÙĨ
    0.07
    iyel
    0.06
    éĽĦ
    0.06
    .Scene
    0.06
    Dismiss
    0.06
    Activations Density 0.003%

    No Known Activations