© 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. 15-LLAMASCOPE-RES-131K
    11. 263
    Prev
    Next
    INDEX
    Explanations

    email addresses and contact-related information

    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
    á»Ļng
    -0.07
    ÛĮØ´ÙĨ
    -0.07
     SD
    -0.06
    _WS
    -0.06
    oose
    -0.06
    flen
    -0.06
    jspx
    -0.06
    ncmp
    -0.06
    á»Ļp
    -0.06
    á»į
    -0.06
    POSITIVE LOGITS
     alone
    0.07
     fore
    0.07
    agg
    0.07
    520
    0.06
    pha
    0.06
    ê¸ī
    0.06
    ego
    0.06
    uster
    0.06
    rc
    0.06
    alone
    0.06
    Activations Density 0.003%

    No Known Activations