© 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. 82073
    Prev
    Next
    INDEX
    Explanations

    references to political leadership and statements from officials

    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
     Hlav
    -0.09
    ì²
    -0.09
    ngle
    -0.07
    _VEC
    -0.07
    DAL
    -0.07
    reff
    -0.07
    Specifier
    -0.07
    onda
    -0.07
     trú
    -0.07
     noci
    -0.07
    POSITIVE LOGITS
     on
    0.06
     amid
    0.06
     said
    0.06
    inar
    0.06
     public
    0.06
     Edgar
    0.05
     frontier
    0.05
    ÑĢд
    0.05
     meeting
    0.05
     Lawyers
    0.05
    Activations Density 0.041%

    No Known Activations