© 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. 128044
    Prev
    Next
    INDEX
    Explanations

    references to online resources and discussions in technical contexts

    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
    ilot
    -0.07
    ä¸įäºĨ
    -0.06
    _SHARE
    -0.06
    #
    -0.06
    -icons
    -0.06
    ictured
    -0.06
     Giovanni
    -0.06
     Doch
    -0.06
    wick
    -0.06
    945
    -0.06
    POSITIVE LOGITS
     http
    0.08
     derec
    0.07
    :http
    0.07
    ogi
    0.07
    -http
    0.07
    http
    0.07
     https
    0.07
    goo
    0.07
     helpful
    0.06
     precedence
    0.06
    Activations Density 0.018%

    No Known Activations