© 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 EvalsExportsinterp-engineNEWAPI 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. 86570
    Prev
    Next
    INDEX
    Explanations

    narratives involving folklore and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References to oral storytelling traditions and narrative forms that preserve and transmit cultural knowledge across generations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Tube
    -0.07
     Rent
    -0.07
    ng
    -0.07
    avors
    -0.07
    udd
    -0.07
     ç©
    -0.06
    ģını
    -0.06
    utf
    -0.06
    eyer
    -0.06
    ille
    -0.06
    POSITIVE LOGITS
     stories
    0.11
    stories
    0.09
     storytelling
    0.09
     story
    0.09
     tales
    0.09
     Story
    0.09
     Stories
    0.09
    æķħäºĭ
    0.08
     bedtime
    0.08
     STORY
    0.08
    Activations Density 0.084%

    No Known Activations