© 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. 38621
    Prev
    Next
    INDEX
    Explanations

    phrases conveying a sense of urgency and missed opportunities

    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
     Blo
    -0.06
    é½
    -0.06
    ifen
    -0.06
    arding
    -0.06
    ssel
    -0.05
    ass
    -0.05
     Burr
    -0.05
    ãĥ³ãĤ°ãĥ«
    -0.05
    Blo
    -0.05
    -p
    -0.05
    POSITIVE LOGITS
     too
    0.13
    too
    0.12
     late
    0.12
     Late
    0.12
     Too
    0.11
    Late
    0.11
    Too
    0.11
    -too
    0.10
    太
    0.10
     TOO
    0.10
    Activations Density 0.030%

    No Known Activations