© 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. 38223
    Prev
    Next
    INDEX
    Explanations

    phrases that describe surprising or unexpected 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
     automát
    -0.06
    åł
    -0.06
    欧ç¾İ
    -0.06
     Ñģозда
    -0.06
     rám
    -0.06
    Matchers
    -0.06
    antz
    -0.06
    аÑĢÑĩ
    -0.06
    eniable
    -0.06
    asto
    -0.06
    POSITIVE LOGITS
     twist
    0.08
     perhaps
    0.08
     bid
    0.07
    Displayed
    0.07
     nod
    0.07
     act
    0.07
     vat
    0.06
     sign
    0.06
     bol
    0.06
    zell
    0.06
    Activations Density 0.014%

    No Known Activations