© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14466
    Prev
    Next
    INDEX
    Explanations

    negative quantifiers and indicators of difficulty or limitation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    .uni
    -0.08
    iêu
    -0.07
    aticon
    -0.07
    umo
    -0.07
     sever
    -0.07
    rray
    -0.07
    .datab
    -0.07
    áp
    -0.07
     dán
    -0.07
    plusplus
    -0.07
    POSITIVE LOGITS
    ("!
    0.06
    treeview
    0.06
    ÏĤ
    0.06
    alsy
    0.06
     Batt
    0.06
    ard
    0.06
    覧
    0.06
    jam
    0.05
    PreparedStatement
    0.05
    acket
    0.05
    Activations Density 0.035%

    No Known Activations