© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28549
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "icon" or its related elements

    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
     
    -0.07
    Âł
    -0.07
    ittle
    -0.06
     Tes
    -0.06
    ÂŃ
    -0.06
     Armed
    -0.06
    tat
    -0.06
     keeping
    -0.06
    [
    -0.06
     cre
    -0.06
    POSITIVE LOGITS
    âĦĸâĦĸ
    0.08
    надлеж
    0.08
    vrier
    0.08
    ;;;;;;;;
    0.07
     Malone
    0.07
    aml
    0.07
    imde
    0.07
    ÑĨез
    0.07
    UsageId
    0.07
    бÑĥдÑĮ
    0.07
    Activations Density 0.001%

    No Known Activations