© 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. 89489
    Prev
    Next
    INDEX
    Explanations

    references to authority and actions taken by officials

    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
    uzzi
    -0.10
     addCriterion
    -0.08
    igung
    -0.07
    mî
    -0.07
     agg
    -0.07
    enek
    -0.07
    $n
    -0.06
    ÙijÙı
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    $r
    -0.06
    POSITIVE LOGITS
    =yes
    0.07
    antt
    0.07
     yes
    0.07
    âĢª
    0.06
    067
    0.06
    erli
    0.06
     sir
    0.06
     ölçüde
    0.06
     Yes
    0.06
    approximately
    0.06
    Activations Density 0.002%

    No Known Activations