© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116514
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation or movement

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ITTER
    -0.06
    boss
    -0.06
    aub
    -0.06
     Gaul
    -0.06
     Bucc
    -0.06
     blow
    -0.06
    สาร
    -0.06
    าà¸Ĥ
    -0.06
    eson
    -0.06
     Crit
    -0.06
    POSITIVE LOGITS
    acific
    0.08
    omo
    0.07
    ieux
    0.07
    stown
    0.07
    ruh
    0.07
    ino
    0.07
    rias
    0.07
    afx
    0.07
    ARRANT
    0.07
    омеÑĢ
    0.07
    Activations Density 0.024%

    No Known Activations