© 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. 103324
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial terminology and discussions of responsibility

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

    Common function words and short connecting phrases that appear in the middle of sentences, serving grammatical rather than primary semantic purposes.

    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
    HING
    -0.07
    Lady
    -0.07
    chaft
    -0.07
    .Layout
    -0.07
    ettings
    -0.07
    BoxLayout
    -0.07
    ignon
    -0.07
     Ïį
    -0.07
    chalk
    -0.06
    embros
    -0.06
    POSITIVE LOGITS
    iten
    0.07
    809
    0.06
     Anch
    0.06
    olson
    0.06
    lesia
    0.06
     dev
    0.06
    aha
    0.06
    cheme
    0.05
    emes
    0.05
     Homo
    0.05
    Activations Density 0.294%

    No Known Activations