© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90424
    Prev
    Next
    INDEX
    Explanations

    topics related to mortality and significant events

    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
    à¥įतà¤ķ
    -0.07
    æij
    -0.07
    uber
    -0.07
    lemen
    -0.07
    (SP
    -0.07
     tatto
    -0.07
     ÑģпиÑģ
    -0.07
    ÅĻÃŃ
    -0.06
     bul
    -0.06
    éĢ¸
    -0.06
    POSITIVE LOGITS
    sei
    0.07
    PTY
    0.07
    shint
    0.07
    ôn
    0.06
    kili
    0.06
    uffles
    0.06
    KT
    0.06
    cheng
    0.06
    loom
    0.06
    aso
    0.06
    Activations Density 0.000%

    No Known Activations