© 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. 26852
    Prev
    Next
    INDEX
    Explanations

    terms that express comparison or quantity

    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
    ĵ°
    -0.08
    opp
    -0.08
    onda
    -0.07
    adel
    -0.07
    ÑĥÑĢÑĥ
    -0.07
    oure
    -0.07
    á»iji
    -0.07
    ovsky
    -0.07
    á»IJ
    -0.06
    ाफ
    -0.06
    POSITIVE LOGITS
    ché
    0.06
    fik
    0.06
    ihad
    0.06
    implicitly
    0.06
    chez
    0.06
    iben
    0.06
     Mac
    0.05
     rigor
    0.05
     on
    0.05
    414
    0.05
    Activations Density 0.007%

    No Known Activations