© 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. 87080
    Prev
    Next
    INDEX
    Explanations

    references to online resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Blog footers or headers containing navigation elements, subscription information, or author descriptions typically appearing between a blog post and other site content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ondo
    -0.09
    ehler
    -0.08
    à¥įवय
    -0.07
    uria
    -0.07
    ulen
    -0.06
    qh
    -0.06
    vs
    -0.06
     Kushner
    -0.06
    itzer
    -0.06
    acz
    -0.06
    POSITIVE LOGITS
     Posts
    0.07
    Posts
    0.07
    positor
    0.07
    Archive
    0.07
     deb
    0.06
     welcome
    0.06
    powered
    0.06
     Episodes
    0.06
    blog
    0.06
     posts
    0.06
    Activations Density 0.015%

    No Known Activations