© 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. 31749
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a challenging start or difficult situation

    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
    mund
    -0.09
    gın
    -0.08
    noinspection
    -0.07
    .scalablytyped
    -0.07
    elight
    -0.07
    inel
    -0.07
     WithEvents
    -0.07
    ازÙĩ
    -0.06
    oux
    -0.06
    cum
    -0.06
    POSITIVE LOGITS
    ahat
    0.07
    /end
    0.06
    URRE
    0.06
     proceedings
    0.06
    932
    0.06
    enco
    0.06
    PopupMenu
    0.06
    anco
    0.06
    nos
    0.06
    urre
    0.06
    Activations Density 0.005%

    No Known Activations