© 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. 89010
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and community in professional contexts

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

    References to professional industries and fields, particularly when discussing community membership, representation, leadership, or career paths within a specific professional sector.

    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
     Abr
    -0.07
     createAction
    -0.06
    reserve
    -0.06
     Abrams
    -0.06
     Gut
    -0.06
     uch
    -0.06
    experimental
    -0.06
     Abs
    -0.06
    /testing
    -0.06
    à¤ĺ
    -0.06
    POSITIVE LOGITS
     industry
    0.11
    industry
    0.09
     Industry
    0.08
    è¡Įä¸ļ
    0.08
    Industry
    0.08
     صÙĨعت
    0.08
    urname
    0.07
    IDER
    0.06
    /pass
    0.06
    è£ħ
    0.06
    Activations Density 0.023%

    No Known Activations