© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88354
    Prev
    Next
    INDEX
    Explanations

    phrases related to experiences of illness or recovery

    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
    atel
    -0.07
    lier
    -0.07
    plor
    -0.07
    uye
    -0.07
    ku
    -0.06
     mel
    -0.06
    à¸Ńà¸Ńà¸ģ
    -0.06
    apia
    -0.06
    otonin
    -0.06
    estination
    -0.06
    POSITIVE LOGITS
    876
    0.07
    brick
    0.07
    isz
    0.07
     to
    0.06
    buzz
    0.06
    ittel
    0.06
    873
    0.06
     بداÙĨ
    0.06
     accustomed
    0.06
    901
    0.06
    Activations Density 0.010%

    No Known Activations