© 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. 104261
    Prev
    Next
    INDEX
    Explanations

    references to local organizations or partnerships

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

    The token "of" functioning as a connector between organization names and their geographic locations, or between maps and their covered areas.

    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
    ichi
    -0.06
    onya
    -0.06
    track
    -0.06
    pon
    -0.05
    alf
    -0.05
    ling
    -0.05
    2
    -0.05
     Track
    -0.05
     crush
    -0.05
     due
    -0.05
    POSITIVE LOGITS
    noop
    0.09
    affer
    0.08
     diseñador
    0.08
    uraa
    0.07
    'gc
    0.07
    ãĤį
    0.07
    inker
    0.07
    ekt
    0.07
    ombat
    0.07
    ÙĥÙĬÙĬÙģ
    0.07
    Activations Density 0.020%

    No Known Activations