© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73997
    Prev
    Next
    INDEX
    Explanations

    references to Pulitzer Prizes in relation to literature and journalism

    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
    aload
    -0.07
    loquent
    -0.07
    ereum
    -0.07
    å´İ
    -0.07
    ntag
    -0.06
    uche
    -0.06
    allax
    -0.06
    lick
    -0.06
     Rated
    -0.06
    ãĥŃãĥ³
    -0.06
    POSITIVE LOGITS
     Pulitzer
    0.07
     awarded
    0.07
     Journalism
    0.06
     Chicago
    0.06
    ãĥĭãĥ¥
    0.06
     winners
    0.06
     announced
    0.06
     winner
    0.06
    sn
    0.06
     award
    0.06
    Activations Density 0.006%

    No Known Activations