© 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. 15-LLAMASCOPE-RES-131K
    11. 90606
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases centered around the word "it."

    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
    ighton
    -0.07
    bury
    -0.07
    sylvania
    -0.06
    ysa
    -0.06
    cea
    -0.06
    able
    -0.06
    evin
    -0.06
    hid
    -0.06
    illas
    -0.06
    ellas
    -0.06
    POSITIVE LOGITS
    inerary
    0.11
    .IsAny
    0.10
    shape
    0.10
    self
    0.09
    imestep
    0.08
    rott
    0.08
    ÑĤал
    0.08
    iner
    0.08
    SELF
    0.08
    antal
    0.07
    Activations Density 0.081%

    No Known Activations