© 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. 89923
    Prev
    Next
    INDEX
    Explanations

    references to years and associated dates

    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
     件
    -0.07
    ová
    -0.06
    itional
    -0.06
    utsch
    -0.06
    IDD
    -0.06
    icional
    -0.06
     Carroll
    -0.06
    utes
    -0.06
    oft
    -0.06
    -await
    -0.06
    POSITIVE LOGITS
     stead
    0.07
    ider
    0.07
    pis
    0.07
    íĥĦ
    0.06
     Kis
    0.06
    ework
    0.06
    antino
    0.06
    èĪ¬
    0.06
    icana
    0.06
    Periph
    0.06
    Activations Density 0.019%

    No Known Activations