© 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. 17-LLAMASCOPE-RES-131K
    11. 81963
    Prev
    Next
    INDEX
    Explanations

    references to art exhibitions and community cultural events

    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
    (&_
    -0.07
    (reinterpret
    -0.07
     ska
    -0.07
    (!_
    -0.07
    ((_
    -0.06
    .BLL
    -0.06
     protagon
    -0.06
    (assign
    -0.06
    plode
    -0.06
     _↵↵
    -0.06
    POSITIVE LOGITS
     (
    0.26
     (↵
    0.14
     ï¼Ī
    0.13
    ï¼Ī
    0.12
     ([
    0.12
    ãĢĭï¼Ī
    0.12
    (
    0.12
     (_,
    0.12
     ê°¤ë¡ľê·¸ë¡ľ
    0.12
    ãĢįï¼Ī
    0.12
    Activations Density 0.398%

    No Known Activations