© 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. 88927
    Prev
    Next
    INDEX
    Explanations

    themes of vulnerability and conflict among contrasting entities

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

    Text elements that mark transitions between content sections, often including punctuation marks, HTML tags, programming variables, or character name pairs that appear at content boundaries or in user-generated content like forums and comments.

    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
     RT
    -0.06
    .movies
    -0.06
    ocache
    -0.06
     Marker
    -0.06
    Preview
    -0.06
    IRT
    -0.06
     Preview
    -0.06
    hem
    -0.06
    aston
    -0.06
     Sa
    -0.05
    POSITIVE LOGITS
    aiser
    0.07
    åĩĨ
    0.07
    tridge
    0.07
     Sır
    0.07
    /ay
    0.07
    _CONV
    0.07
     Cyan
    0.06
     Steele
    0.06
    /cms
    0.06
    AREN
    0.06
    Activations Density 0.113%

    No Known Activations