© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 118690
    Prev
    Next
    INDEX
    Explanations

    references to customer service interactions and support

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

    Interface elements and metadata from online question-answer forums, including usernames, timestamps, voting indicators, and structural markers that organize content.

    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
    aph
    -0.06
    .linkedin
    -0.05
    caption
    -0.05
     equilibrium
    -0.05
    ota
    -0.05
     Sheep
    -0.05
    ény
    -0.05
    recover
    -0.05
     checklist
    -0.05
    ause
    -0.05
    POSITIVE LOGITS
     answer
    0.15
     answered
    0.15
     ANSW
    0.15
     Answer
    0.14
     answers
    0.14
    answer
    0.13
    _answer
    0.13
    åĽŀçŃĶ
    0.12
    answers
    0.12
    answered
    0.12
    Activations Density 0.019%

    No Known Activations