© 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. 123510
    Prev
    Next
    INDEX
    Explanations

    phrases expressing mixed or nuanced evaluations of situations

    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
    /vnd
    -0.06
    uck
    -0.06
    alse
    -0.06
    rey
    -0.06
    rescia
    -0.06
    lem
    -0.06
    try
    -0.06
     Nicholson
    -0.06
     heck
    -0.06
    efs
    -0.06
    POSITIVE LOGITS
     GOOD
    0.09
     good
    0.08
    GOOD
    0.07
     Good
    0.07
    ipa
    0.07
     blessings
    0.07
     Bad
    0.06
    Uni
    0.06
     undesirable
    0.06
     BAD
    0.06
    Activations Density 0.091%

    No Known Activations