© 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. 88520
    Prev
    Next
    INDEX
    Explanations

    elements of social interactions and gatherings

    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
     original
    -0.06
    گرد
    -0.06
    å
    -0.06
     interpolation
    -0.06
     acid
    -0.06
     superv
    -0.06
     interpol
    -0.06
    FLOAT
    -0.05
    esting
    -0.05
    Ãł
    -0.05
    POSITIVE LOGITS
    ivet
    0.07
    è¿Ļæĺ¯
    0.07
    .IsAny
    0.07
    nev
    0.07
    γκε
    0.07
    Soon
    0.06
    _KeyDown
    0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.06
    uyu
    0.06
    лагод
    0.06
    Activations Density 0.039%

    No Known Activations