© 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. 74801
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognition in literature and cinema

    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
    ifen
    -0.07
    æ±
    -0.07
    asin
    -0.06
    plib
    -0.06
    eton
    -0.06
    anza
    -0.06
    åł´
    -0.06
    mate
    -0.06
    nds
    -0.06
    _INCLUDED
    -0.06
    POSITIVE LOGITS
    uros
    0.08
    322
    0.07
    Matchers
    0.07
    304
    0.07
    .appspot
    0.06
     Harding
    0.06
    .wordpress
    0.06
    929
    0.06
    enever
    0.06
    енÑĮ
    0.06
    Activations Density 0.045%

    No Known Activations