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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105802
    Prev
    Next
    INDEX
    Explanations

    terms associated with procrastination and negative behaviors

    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
    lements
    -0.08
    lify
    -0.07
    nof
    -0.07
    stalk
    -0.07
    enton
    -0.07
     Chronicle
    -0.07
    ière
    -0.07
    oug
    -0.07
    ób
    -0.07
    ekyll
    -0.06
    POSITIVE LOGITS
    ism
    0.07
     tendencies
    0.07
    itis
    0.06
    ACTION
    0.06
    (delay
    0.06
    gan
    0.06
    -delay
    0.06
     avoidance
    0.06
    inx
    0.06
     Tactics
    0.06
    Activations Density 0.001%

    No Known Activations