© 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. 120611
    Prev
    Next
    INDEX
    Explanations

    articles indicating the presence of various types of businesses and initiatives

    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
     Nej
    -0.07
    upal
    -0.07
    ware
    -0.07
    å½¹
    -0.06
    Ÿ
    -0.06
    ou
    -0.06
    kins
    -0.06
    ÑĥÑĢн
    -0.06
    jezd
    -0.06
     hell
    -0.06
    POSITIVE LOGITS
     oneself
    0.09
    /respond
    0.07
    _regularizer
    0.07
    -addons
    0.07
    ustin
    0.07
    anio
    0.07
     erfolgre
    0.07
    .ua
    0.07
    avar
    0.07
    lsi
    0.06
    Activations Density 0.032%

    No Known Activations