© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59598
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "find"

    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
    pery
    -0.07
    ulate
    -0.07
    ÑĢоÑĩ
    -0.07
    icans
    -0.07
    484
    -0.07
     versa
    -0.07
    unnel
    -0.06
     fraction
    -0.06
    culus
    -0.06
    aphael
    -0.06
    POSITIVE LOGITS
    ings
    0.10
    ers
    0.08
    ividual
    0.07
    iture
    0.07
    horn
    0.07
    amp
    0.07
    erv
    0.07
     kiếm
    0.07
    ogue
    0.07
    rst
    0.07
    Activations Density 0.010%

    No Known Activations