© 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. 42152
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of the word "are" in various contexts

    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
    egra
    -0.07
    erset
    -0.07
    ingroup
    -0.07
    dia
    -0.07
    леж
    -0.07
    ograd
    -0.06
    Ñĸнки
    -0.06
    dden
    -0.06
    laus
    -0.06
    arest
    -0.06
    POSITIVE LOGITS
     two
    0.09
     several
    0.08
     broadly
    0.08
     three
    0.07
     many
    0.07
     four
    0.07
     main
    0.06
     Several
    0.06
    ument
    0.06
    uments
    0.06
    Activations Density 0.015%

    No Known Activations