© 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. 103849
    Prev
    Next
    INDEX
    Explanations

    references to various types of receptors related to health and medicine

    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
     Herald
    -0.07
    otope
    -0.06
    enci
    -0.06
    ofi
    -0.06
    uild
    -0.06
    .habbo
    -0.06
    blas
    -0.06
    otta
    -0.06
    pedia
    -0.06
    arde
    -0.06
    POSITIVE LOGITS
     receptors
    0.07
     receptor
    0.06
     Family
    0.06
    elts
    0.06
     reopen
    0.06
    ìĹ´
    0.06
    инов
    0.06
     Joanna
    0.06
    ->__
    0.06
    -Re
    0.06
    Activations Density 0.019%

    No Known Activations