© 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. 30762
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "be" in various forms

    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
    man
    -0.08
    alytics
    -0.07
    ngo
    -0.07
    son
    -0.07
     Genç
    -0.07
    rosse
    -0.07
    manent
    -0.06
    .setCode
    -0.06
    ships
    -0.06
    uj
    -0.06
    POSITIVE LOGITS
    ckett
    0.07
    eker
    0.07
    ekil
    0.07
    ethoven
    0.07
    opic
    0.07
    aming
    0.06
    anie
    0.06
    ettle
    0.06
    ertype
    0.06
    ehler
    0.06
    Activations Density 0.017%

    No Known Activations