© 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. 3454
    Prev
    Next
    INDEX
    Explanations

    expressions about recent updates or announcements in a context

    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
     specialist
    -0.06
     specialists
    -0.06
    âĢ¦↵
    -0.06
     Specialists
    -0.05
     Rating
    -0.05
    udeau
    -0.05
     pÅĤ
    -0.05
     ÙħÙĤابÙĦ
    -0.05
     challenging
    -0.05
     dual
    -0.05
    POSITIVE LOGITS
     news
    0.11
    -news
    0.10
     headlines
    0.10
    news
    0.10
     reported
    0.09
     kontakte
    0.09
    _news
    0.08
    reported
    0.08
     updates
    0.08
    /news
    0.08
    Activations Density 0.015%

    No Known Activations