© 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 EvalsExportsAPI 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. 59183
    Prev
    Next
    INDEX
    Explanations

    discussions about impeachment proceedings

    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
    átka
    -0.07
    ÏĥηÏĤ
    -0.06
    _PT
    -0.06
     Bapt
    -0.06
    лика
    -0.06
    osate
    -0.06
    uluk
    -0.06
     Pratt
    -0.06
     patented
    -0.06
    ushman
    -0.06
    POSITIVE LOGITS
     impeachment
    0.11
     impe
    0.10
    342
    0.07
    inium
    0.07
    ubble
    0.07
    tae
    0.07
    ugins
    0.07
     process
    0.06
     formal
    0.06
     Formal
    0.06
    Activations Density 0.013%

    No Known Activations