© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30066
    Prev
    Next
    INDEX
    Explanations

    references to Donald Trump and related political events

    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
    -valu
    -0.07
    asiswa
    -0.07
    RowAt
    -0.07
    ighton
    -0.07
    \Migration
    -0.07
    braco
    -0.07
    gota
    -0.07
    uten
    -0.06
    nesty
    -0.06
    smouth
    -0.06
    POSITIVE LOGITS
     пÑĢавда
    0.07
    ẽ
    0.06
     Usa
    0.06
     US
    0.06
    .gdx
    0.06
    ãģ¾ãģļ
    0.06
    ((((
    0.06
     æĸ¹
    0.06
    TPL
    0.06
     partly
    0.06
    Activations Density 0.129%

    No Known Activations