© 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. 63221
    Prev
    Next
    INDEX
    Explanations

    language related to pressure and expectations

    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
     paci
    -0.06
     argument
    -0.06
    istrat
    -0.06
     Arguments
    -0.06
    indsight
    -0.06
    opsis
    -0.06
     Argument
    -0.06
    Æ¡
    -0.06
    ArgumentException
    -0.06
     Saud
    -0.06
    POSITIVE LOGITS
     pressure
    0.20
     Pressure
    0.19
    Pressure
    0.17
    pressure
    0.17
    -pressure
    0.16
     pressures
    0.16
    _pressure
    0.14
     pressured
    0.12
     PRESS
    0.09
    åİĭ
    0.09
    Activations Density 0.023%

    No Known Activations