© 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. 81048
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to fact-checking

    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
    opard
    -0.07
    alty
    -0.07
    alta
    -0.06
    οÏħÏĥ
    -0.06
    ><![
    -0.06
    ÑĤÑĢон
    -0.06
    etus
    -0.06
    lease
    -0.06
    説
    -0.06
     crust
    -0.06
    POSITIVE LOGITS
    oger
    0.07
    Ãĭ
    0.07
    .Invariant
    0.06
     VERIFY
    0.06
     Journalism
    0.06
     verdad
    0.06
     sco
    0.06
     scr
    0.06
     primaries
    0.06
    anton
    0.06
    Activations Density 0.004%

    No Known Activations