© 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. 88982
    Prev
    Next
    INDEX
    Explanations

    references to gathering or audience interactions in a context related to artistic performance or 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
     мног
    -0.07
    लà¤Ĺ
    -0.07
    tera
    -0.07
     nearly
    -0.06
     Lots
    -0.06
    ieten
    -0.06
    lots
    -0.06
    Lots
    -0.06
    orial
    -0.06
    iard
    -0.06
    POSITIVE LOGITS
     tiny
    0.16
     few
    0.16
     occasional
    0.15
     small
    0.15
     only
    0.14
    tiny
    0.14
     limited
    0.13
     handful
    0.13
    ONLY
    0.13
     quelques
    0.13
    Activations Density 0.001%

    No Known Activations