© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 82423
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and publications in specific industries

    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
     correspondence
    -0.06
     mil
    -0.06
    avers
    -0.05
     //!<
    -0.05
     Networks
    -0.05
     pled
    -0.05
    ¼åIJĪ
    -0.05
    æ°ı
    -0.05
    WithIdentifier
    -0.05
    aunch
    -0.05
    POSITIVE LOGITS
     data
    0.10
    æĬ¥åijĬ
    0.09
     Data
    0.08
     industry
    0.08
    -data
    0.08
     insights
    0.08
    æķ°æį®
    0.08
    _mE
    0.08
    astreet
    0.08
     Trend
    0.08
    Activations Density 0.022%

    No Known Activations