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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31232
    Prev
    Next
    INDEX
    Explanations

    terms related to skin care and exfoliation

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

    Names of people, places, and technical entities that provide specific identifying information in different contexts.

    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
     erotik
    -0.12
    :↵↵↵↵↵↵
    -0.12
     treff
    -0.11
     dán
    -0.11
    ılıģıyla
    -0.11
     bekl
    -0.11
     بÙĨابر
    -0.11
    بÛĮÙĨÛĮ
    -0.10
     tük
    -0.10
     seksi
    -0.10
    POSITIVE LOGITS
     locally
    0.07
     internally
    0.07
     in
    0.06
     sequentially
    0.06
     regularly
    0.06
     for
    0.06
     temporarily
    0.06
     simultaneously
    0.06
     on
    0.06
     notably
    0.06
    Activations Density 16.224%

    No Known Activations