© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105624
    Prev
    Next
    INDEX
    Explanations

    references to key plot elements and character relationships in a film series

    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
    æ´ª
    -0.07
     Kou
    -0.07
    oux
    -0.07
    jin
    -0.07
    ê¸ī
    -0.06
    lix
    -0.06
    ense
    -0.06
    omik
    -0.06
    505
    -0.06
    imen
    -0.06
    POSITIVE LOGITS
     heir
    0.06
    iani
    0.06
     Conserv
    0.06
    isbury
    0.06
     Isl
    0.06
    elda
    0.06
     isl
    0.06
    inherit
    0.06
    adioButton
    0.06
     gene
    0.06
    Activations Density 0.014%

    No Known Activations