© 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. 107985
    Prev
    Next
    INDEX
    Explanations

    mentions of Texas Democrats and their political actions

    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
    amac
    -0.08
     kå
    -0.07
    ä¸ĩ
    -0.06
    ISA
    -0.06
    olla
    -0.06
     favour
    -0.06
    ÃĸL
    -0.06
    anja
    -0.06
    allas
    -0.06
    .inline
    -0.06
    POSITIVE LOGITS
     welcome
    0.07
    ordo
    0.06
     border
    0.06
    exas
    0.06
    welcome
    0.06
    border
    0.06
     ISSN
    0.06
    CRT
    0.06
     "('
    0.06
    ["$
    0.06
    Activations Density 0.002%

    No Known Activations