© 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. 128782
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of individuals

    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
    buz
    -0.08
    бÑĸ
    -0.08
    imd
    -0.08
    ãģ£ãģ±
    -0.08
    #ac
    -0.08
    &e
    -0.07
    lisi
    -0.07
    ız
    -0.07
    #ab
    -0.07
    roi
    -0.07
    POSITIVE LOGITS
    .AutoSizeMode
    0.07
    âĢ¦↵↵
    0.06
    /stdc
    0.06
    âĢ¯
    0.05
     “
    0.05
    Âłob
    0.05
    Âłs
    0.05
    Âłt
    0.05
    jspx
    0.05
    nga
    0.05
    Activations Density 0.007%

    No Known Activations