© 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. 81917
    Prev
    Next
    INDEX
    Explanations

    references to repeated expressions of gratitude or thanks

    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
    755
    -0.06
    ins
    -0.06
    555
    -0.05
    hed
    -0.05
    ent
    -0.05
    trib
    -0.05
     Chamber
    -0.05
     artık
    -0.05
     Start
    -0.05
    li
    -0.05
    POSITIVE LOGITS
     pornofilm
    0.07
    /WebAPI
    0.07
    elligence
    0.07
    urovision
    0.07
    ÙĪرت
    0.07
    937
    0.07
    irth
    0.07
    APPER
    0.07
    (disposing
    0.07
    straints
    0.07
    Activations Density 0.002%

    No Known Activations