© 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. 119993
    Prev
    Next
    INDEX
    Explanations

    references to cinematic narratives and 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
    -
    -0.05
    SS
    -0.05
    LS
    -0.05
    SE
    -0.05
    IV
    -0.05
    @
    -0.05
    ãĥ¥
    -0.05
     means
    -0.05
    ods
    -0.05
     demo
    -0.05
    POSITIVE LOGITS
     tradition
    0.14
     Tradition
    0.12
     traditions
    0.12
     lineage
    0.09
     tradi
    0.09
     footsteps
    0.09
    trad
    0.09
     heritage
    0.09
    继
    0.08
    sig
    0.08
    Activations Density 0.037%

    No Known Activations