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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84591
    Prev
    Next
    INDEX
    Explanations

    expressions of complexity or difficulty in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases and tokens indicating complexity, uncertainty, or difficult situations requiring careful consideration.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ̧
    -0.06
     tet
    -0.06
     rig
    -0.06
    aret
    -0.06
     pall
    -0.06
     Damen
    -0.06
    761
    -0.06
     course
    -0.06
     Diy
    -0.06
     rational
    -0.05
    POSITIVE LOGITS
     tricky
    0.13
     difficult
    0.13
     dific
    0.10
     difÃŃc
    0.09
     harder
    0.09
     difÃŃcil
    0.09
     difficile
    0.09
     complicated
    0.09
     hardest
    0.08
     difficulty
    0.08
    Activations Density 0.038%

    No Known Activations