© 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. 89652
    Prev
    Next
    INDEX
    Explanations

    expressions related to verifying understanding or correctness

    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
    issen
    -0.07
    RSA
    -0.06
     Claus
    -0.06
    ave
    -0.06
     agency
    -0.06
    ÑĢÑĥн
    -0.06
    ิมà¸ŀ
    -0.06
    anger
    -0.06
    uch
    -0.06
    ude
    -0.05
    POSITIVE LOGITS
     correct
    0.17
     Correct
    0.15
    Correct
    0.14
    correct
    0.14
     correctly
    0.13
    (correct
    0.13
    _correct
    0.12
     correctness
    0.12
    orrect
    0.11
    æŃ£ç¡®
    0.11
    Activations Density 0.013%

    No Known Activations