© 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. 80269
    Prev
    Next
    INDEX
    Explanations

    references to governmental or official structures and their activities

    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
    ensa
    -0.07
    deen
    -0.07
    à¸Ļà¸Ń
    -0.07
    вок
    -0.07
    ropoda
    -0.07
    sembly
    -0.07
    ccount
    -0.07
    ihad
    -0.06
     Rencontres
    -0.06
    eza
    -0.06
    POSITIVE LOGITS
     White
    0.08
     Oval
    0.07
    WASHINGTON
    0.07
     Garten
    0.07
     Washington
    0.07
    .gov
    0.07
    White
    0.06
    bie
    0.06
     Gros
    0.06
     precedent
    0.06
    Activations Density 0.002%

    No Known Activations