© 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. 60904
    Prev
    Next
    INDEX
    Explanations

    instances of specific punctuation or formatting within text

    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
    ÑĤÑı
    -0.09
    YP
    -0.09
     fisse
    -0.08
    ëĥ¥
    -0.08
    еÑĢп
    -0.07
    gether
    -0.07
    entai
    -0.07
    _recent
    -0.07
    icha
    -0.07
    /UIKit
    -0.07
    POSITIVE LOGITS
     radi
    0.06
    beck
    0.06
     Rim
    0.06
    ieux
    0.06
    ://
    0.05
    'n
    0.05
     Portal
    0.05
     incl
    0.05
     fa
    0.05
     fit
    0.05
    Activations Density 0.000%

    No Known Activations