© 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. 91830
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate disappointment or criticism in corporate scenarios

    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
    ädchen
    -0.06
     comparison
    -0.06
     especially
    -0.06
     Heck
    -0.06
     dil
    -0.06
     esp
    -0.06
     lẫn
    -0.06
     particularly
    -0.05
     å¹
    -0.05
     Ñģвоими
    -0.05
    POSITIVE LOGITS
     hence
    0.08
    ackers
    0.07
    imony
    0.07
    ìĿ´ê³ł
    0.07
    itals
    0.07
    bas
    0.07
    isci
    0.06
     BITTE
    0.06
    ainen
    0.06
     ragaz
    0.06
    Activations Density 0.029%

    No Known Activations