© 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. 17-LLAMASCOPE-RES-131K
    11. 61076
    Prev
    Next
    INDEX
    Explanations

    references to literary themes or elements involving fiction

    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
    enic
    -0.06
    ë
    -0.06
    ibbon
    -0.06
    egasus
    -0.06
     conduct
    -0.06
    IR
    -0.06
     Cached
    -0.05
    ÏĨι
    -0.05
    óż
    -0.05
    nees
    -0.05
    POSITIVE LOGITS
     novel
    0.07
    'gc
    0.07
    .cx
    0.06
    nov
    0.06
    /Gate
    0.06
    /Peak
    0.06
     cvs
    0.06
    .datatables
    0.06
    ecz
    0.06
    ellation
    0.06
    Activations Density 0.008%

    No Known Activations