© 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 EvalsExportsinterp-engineNEWAPI 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. 17856
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically the comma

    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
    ÑıÑħ
    -0.07
     recent
    -0.06
    hs
    -0.06
     hypothetical
    -0.06
     seperate
    -0.06
     helf
    -0.06
    arra
    -0.06
    \\\\
    -0.06
    uthor
    -0.06
    perc
    -0.06
    POSITIVE LOGITS
     universities
    0.07
     later
    0.07
    Wunused
    0.06
     university
    0.06
     University
    0.06
    é¨
    0.06
    大åħ¨
    0.06
     ÑĥнÑĸвеÑĢÑģиÑĤеÑĤ
    0.06
     Garrison
    0.06
    áf
    0.06
    Activations Density 0.000%

    No Known Activations