© 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. 15-LLAMASCOPE-RES-131K
    11. 103488
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and resilience

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

    Sentence-ending or clause-separating punctuation marks (primarily periods and commas) that create structure in text and indicate logical breaks between ideas.

    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
    ELY
    -0.07
    ivities
    -0.07
    SizeMode
    -0.07
    اسÙħ
    -0.07
    åŃ
    -0.07
    ữ
    -0.07
    ÏĦεÏģ
    -0.07
    WithPath
    -0.07
    andi
    -0.07
    BOSE
    -0.07
    POSITIVE LOGITS
     dipped
    0.06
    utor
    0.06
    ardown
    0.06
    usra
    0.06
     interval
    0.06
    573
    0.06
     Dip
    0.06
    borg
    0.06
    pline
    0.06
    rosso
    0.06
    Activations Density 0.041%

    No Known Activations