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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88469
    Prev
    Next
    INDEX
    Explanations

    dialogues and interactions among characters in storytelling

    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
     tonight
    -0.08
     tomorrow
    -0.07
     yesterday
    -0.06
    ilib
    -0.06
    ollen
    -0.06
    eldom
    -0.06
     завÑĤÑĢа
    -0.06
    ifton
    -0.05
    ä»Ĭ
    -0.05
    iry
    -0.05
    POSITIVE LOGITS
    then
    0.08
     THEN
    0.07
    likle
    0.07
     гÑĸд
    0.07
    æľĢåĪĿ
    0.07
    Then
    0.06
    íĴ
    0.06
    çĦ¶åIJİ
    0.06
    roe
    0.06
    guess
    0.06
    Activations Density 0.031%

    No Known Activations