© 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. 15-LLAMASCOPE-RES-131K
    11. 86516
    Prev
    Next
    INDEX
    Explanations

    references to political dissent and associated legal consequences

    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
    vard
    -0.08
    antz
    -0.07
    onas
    -0.07
    asal
    -0.07
    isposable
    -0.07
    avra
    -0.07
    ãĥ¼ãĥIJ
    -0.07
    uzey
    -0.07
    argas
    -0.07
    CardBody
    -0.07
    POSITIVE LOGITS
     foreign
    0.06
     interp
    0.06
     Hed
    0.05
     distorted
    0.05
     Ku
    0.05
     sw
    0.05
     Jur
    0.05
     political
    0.05
     sed
    0.05
    емÑĥ
    0.05
    Activations Density 0.021%

    No Known Activations