© 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. 72093
    Prev
    Next
    INDEX
    Explanations

    political references and arguments concerning the Republican Party

    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
    uso
    -0.06
    enson
    -0.06
    beit
    -0.06
    avax
    -0.06
    ogenerated
    -0.06
    arehouse
    -0.06
    ocz
    -0.06
    fuscated
    -0.06
    .jupiter
    -0.06
    à¸Ĭà¸Ļ
    -0.06
    POSITIVE LOGITS
     accumulating
    0.07
    UBL
    0.07
    vak
    0.06
     aggregate
    0.06
    ifr
    0.06
     ëĤ´ëł¤
    0.06
    жÑĥ
    0.06
    /fire
    0.06
     mdi
    0.06
    268
    0.06
    Activations Density 0.055%

    No Known Activations