© 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. 104510
    Prev
    Next
    INDEX
    Explanations

    references to assistance and customer support related to business services

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

    Courteous customer service phrases expressing willingness to assist, often appearing in business contexts as closing statements or invitations for contact.

    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
    um
    -0.06
     Wat
    -0.06
    ruh
    -0.06
    urs
    -0.05
     pleading
    -0.05
    interopRequire
    -0.05
     æĹ
    -0.05
     nie
    -0.05
    CRT
    -0.05
     Bucc
    -0.05
    POSITIVE LOGITS
    γκα
    0.08
    opup
    0.07
    _echo
    0.07
    TAIL
    0.07
    igin
    0.07
     helfen
    0.07
    adar
    0.07
    esters
    0.07
    .TryParse
    0.07
     Assist
    0.07
    Activations Density 0.093%

    No Known Activations