© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1417
    Prev
    Next
    INDEX
    Explanations

    statements of confidence or expression of belief

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    -fontawesome
    -0.08
     INTERRUPTION
    -0.07
    OfClass
    -0.07
    .aut
    -0.07
    ivec
    -0.07
    cete
    -0.07
    ewe
    -0.07
    ocale
    -0.07
    mojom
    -0.07
    ä¹Łæľī
    -0.07
    POSITIVE LOGITS
     recent
    0.07
     recently
    0.06
    uding
    0.06
     tod
    0.06
     contrary
    0.05
    ạc
    0.05
    iyah
    0.05
    opher
    0.05
    urger
    0.05
    ottle
    0.05
    Activations Density 0.017%

    No Known Activations