© 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. 41091
    Prev
    Next
    INDEX
    Explanations

    references to gentleness and gentle experiences

    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
    naments
    -0.08
    dete
    -0.07
    ÑĨеÑģ
    -0.07
    лл
    -0.07
    RunLoop
    -0.07
    deal
    -0.07
    orting
    -0.07
    osphate
    -0.06
    onical
    -0.06
    .mousePosition
    -0.06
    POSITIVE LOGITS
    ewed
    0.09
     gentle
    0.08
    ofday
    0.07
    wares
    0.07
     gently
    0.07
    folk
    0.07
     gent
    0.07
    íŀĪ
    0.07
    ocker
    0.07
     touch
    0.06
    Activations Density 0.009%

    No Known Activations