© 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. 61712
    Prev
    Next
    INDEX
    Explanations

    variations of the word "turn."

    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
    oop
    -0.08
    ged
    -0.08
    eur
    -0.08
    oa
    -0.07
    gt
    -0.07
    unas
    -0.07
    imized
    -0.07
    ging
    -0.07
    ../../../
    -0.07
    å¤ĩ
    -0.06
    POSITIVE LOGITS
    stile
    0.14
    pike
    0.12
    tables
    0.09
    table
    0.08
    moil
    0.08
    coat
    0.07
    abouts
    0.07
    ächst
    0.07
    baugh
    0.07
    OMEM
    0.07
    Activations Density 0.033%

    No Known Activations