© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77926
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences and reflections

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

    Tokens that introduce or qualify personal experiences, insights, or advice, often using first-person perspective or indicating subjective effectiveness.

    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
    wan
    -0.06
    egot
    -0.06
    andex
    -0.06
    sic
    -0.06
    ık
    -0.05
    ÑģоÑĢ
    -0.05
    mainwindow
    -0.05
    egen
    -0.05
    обÑħодим
    -0.05
    isy
    -0.05
    POSITIVE LOGITS
     mine
    0.23
     myself
    0.23
    mine
    0.18
     personally
    0.18
    Personally
    0.17
    Mine
    0.17
     ours
    0.16
    æĪij
    0.16
     my
    0.16
     Personally
    0.15
    Activations Density 0.101%

    No Known Activations