© 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. 18524
    Prev
    Next
    INDEX
    Explanations

    contrasting or qualifying phrases that introduce exceptions

    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
    oba
    -0.07
    elu
    -0.07
    ITCH
    -0.06
    phia
    -0.06
    oeff
    -0.06
    ะà¹ģ
    -0.06
    olu
    -0.06
    odom
    -0.06
    IDS
    -0.06
    hlen
    -0.06
    POSITIVE LOGITS
     not
    0.10
    chers
    0.08
     nicht
    0.07
    not
    0.07
    -not
    0.07
    569
    0.06
     Not
    0.06
     âīł
    0.06
    yn
    0.06
    icket
    0.06
    Activations Density 0.012%

    No Known Activations