© 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. 17-LLAMASCOPE-RES-131K
    11. 93432
    Prev
    Next
    INDEX
    Explanations

    specific named brands or companies

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

    Names of organizations, publications, companies, or institutions that appear at the end of titles, URLs, or citations, often in a format resembling a directory or reference list.

    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
    @student
    -0.09
    tember
    -0.07
    ederland
    -0.07
    اÙĪ
    -0.07
    @[
    -0.07
    ritic
    -0.07
    abee
    -0.06
    öyle
    -0.06
    elves
    -0.06
    eding
    -0.06
    POSITIVE LOGITS
     Inc
    0.07
     official
    0.06
     Kendrick
    0.06
    tam
    0.06
    244
    0.06
    117
    0.06
    uzey
    0.06
    142
    0.06
    313
    0.06
     worthy
    0.06
    Activations Density 0.036%

    No Known Activations