© 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. 4524
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    ishly
    -0.08
    amma
    -0.07
    udur
    -0.07
    icast
    -0.07
    baugh
    -0.07
    achuset
    -0.07
    anness
    -0.07
     ?><?
    -0.07
    itra
    -0.07
    est
    -0.07
    POSITIVE LOGITS
    IRE
    0.07
     better
    0.07
    acea
    0.06
    yre
    0.06
     piv
    0.06
    zÄħd
    0.06
    oley
    0.06
     Better
    0.06
    uzz
    0.05
     depart
    0.05
    Activations Density 0.003%

    No Known Activations