© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4322
    Prev
    Next
    INDEX
    Explanations

    narrative and plot details in a story

    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
    elong
    -0.07
     prostitut
    -0.07
    egin
    -0.07
    ewire
    -0.07
    ernote
    -0.07
    nodoc
    -0.07
    롱
    -0.07
    .scalablytyped
    -0.07
    ulk
    -0.07
    νε
    -0.06
    POSITIVE LOGITS
     ending
    0.16
     endings
    0.13
     Ending
    0.13
     plot
    0.12
    Ending
    0.12
    plot
    0.11
     resolution
    0.11
     clim
    0.11
     climax
    0.10
     ended
    0.10
    Activations Density 0.229%

    No Known Activations