© 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. 128065
    Prev
    Next
    INDEX
    Explanations

    personal introductions and names

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

    Names or identifiers that appear at the end of podcast/media segments, often indicating hosts, authors, characters, or speakers in transcripts, sometimes followed by location identifiers or contextual information.

    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
    ded
    -0.07
    067
    -0.06
    497
    -0.06
    ut
    -0.06
    :|
    -0.06
    ha
    -0.06
    enegro
    -0.06
    ils
    -0.06
    ablo
    -0.06
    iez
    -0.05
    POSITIVE LOGITS
    esome
    0.07
    çĴ°
    0.07
    .DropDown
    0.07
    ÙĪÙĬت
    0.07
    _subtitle
    0.07
    inkle
    0.07
    Ỽ
    0.06
    _SIGNATURE
    0.06
    ostel
    0.06
    Subtitle
    0.06
    Activations Density 0.007%

    No Known Activations