© 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. 53909
    Prev
    Next
    INDEX
    Explanations

    instances of present continuous tense or active voice

    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
     Gott
    -0.08
     dilig
    -0.07
    æĮĻ
    -0.07
    'gc
    -0.06
    $MESS
    -0.06
    onas
    -0.06
     dán
    -0.06
     å¾ĴæŃ©
    -0.06
     dziew
    -0.06
     kém
    -0.06
    POSITIVE LOGITS
     env
    0.07
    wagon
    0.07
    ARSE
    0.06
    feld
    0.06
    Ļ¨
    0.06
    habi
    0.06
    rowned
    0.06
    ale
    0.06
    phe
    0.06
    cea
    0.06
    Activations Density 0.000%

    No Known Activations