© 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. 1197
    Prev
    Next
    INDEX
    Explanations

    elements related to written or artistic expressions and their qualities

    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
    azer
    -0.06
    olib
    -0.06
    .Lib
    -0.06
    olta
    -0.06
    ement
    -0.06
     flag
    -0.06
    oola
    -0.06
    mi
    -0.05
    via
    -0.05
     bubbles
    -0.05
    POSITIVE LOGITS
    noun
    0.07
    htar
    0.07
    loff
    0.07
    InThe
    0.07
    .appspot
    0.07
    .opts
    0.06
     накоп
    0.06
    irie
    0.06
    bsites
    0.06
    Äįan
    0.06
    Activations Density 0.053%

    No Known Activations