© 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 EvalsExportsinterp-engineNEWAPI 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. 73069
    Prev
    Next
    INDEX
    Explanations

    references to comfort and discomfort in various contexts

    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
    udit
    -0.07
    istingu
    -0.06
    usz
    -0.06
    mür
    -0.06
    ajs
    -0.06
     اÙĦÙħØ´
    -0.06
    irez
    -0.06
    orida
    -0.06
    xn
    -0.06
    çīĩ
    -0.06
    POSITIVE LOGITS
     confines
    0.08
     uncomfortable
    0.07
    วรร
    0.06
    land
    0.06
     accustomed
    0.06
     bounds
    0.06
    edReader
    0.06
    oland
    0.06
    iens
    0.06
    ãĥ¼ãĥ©
    0.06
    Activations Density 0.002%

    No Known Activations