© 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 EvalsExportsinterp-engineNEWAPI 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. 120238
    Prev
    Next
    INDEX
    Explanations

    instances of the word "created" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rade
    -0.06
    via
    -0.06
    çĿ
    -0.06
    ingu
    -0.06
    Ñŀ
    -0.06
    οÏĤ
    -0.06
    umber
    -0.06
    ular
    -0.06
    vil
    -0.06
    hel
    -0.06
    POSITIVE LOGITS
    emean
    0.07
    ewidth
    0.07
    å©
    0.07
    å³
    0.07
    edback
    0.06
    .untracked
    0.06
    gens
    0.06
     klin
    0.06
    \Php
    0.06
    -tm
    0.06
    Activations Density 0.001%

    No Known Activations