© 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 EvalsExportsAPI 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. 86066
    Prev
    Next
    INDEX
    Explanations

    the name "Tommy" and variations of the word "tomato."

    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
    ties
    -0.07
    unning
    -0.07
    uary
    -0.06
    loi
    -0.06
    iman
    -0.06
    521
    -0.06
    iaux
    -0.06
    weet
    -0.06
    rious
    -0.06
    ırı
    -0.06
    POSITIVE LOGITS
    asso
    0.10
    atoes
    0.10
    islav
    0.08
    ás
    0.08
    Tom
    0.08
    iko
    0.07
     Cruise
    0.07
     Powers
    0.07
    tom
    0.07
    aso
    0.07
    Activations Density 0.029%

    No Known Activations