© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    references to events, particularly those related to food and meals during specific times

    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
     season
    -0.11
    _season
    -0.10
     Season
    -0.09
     summer
    -0.09
     seasons
    -0.08
    Season
    -0.08
     summers
    -0.08
    å¤ı
    -0.08
    season
    -0.08
     spring
    -0.08
    POSITIVE LOGITS
     week
    0.12
     weekend
    0.11
    æĺŁæľŁ
    0.11
     Monday
    0.10
    åij¨
    0.10
     Friday
    0.10
     Thursday
    0.09
    ìļĶìĿ¼
    0.09
     Week
    0.09
    -week
    0.09
    Activations Density 0.036%

    No Known Activations