© 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. 30408
    Prev
    Next
    INDEX
    Explanations

    aspects related to political commentary and analysis

    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
    ovu
    -0.08
    oshi
    -0.07
    incerely
    -0.07
    icator
    -0.07
    orial
    -0.07
    rán
    -0.06
    opus
    -0.06
    uide
    -0.06
     POT
    -0.06
    CADE
    -0.06
    POSITIVE LOGITS
     only
    0.11
     лиÑĪÑĮ
    0.10
     fewer
    0.10
     apenas
    0.10
     (<
    0.09
    only
    0.08
    limited
    0.08
     nor
    0.08
     Only
    0.08
    Only
    0.08
    Activations Density 0.062%

    No Known Activations