© 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. 89025
    Prev
    Next
    INDEX
    Explanations

    references to political figures and election contexts

    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
    oppel
    -0.07
     licens
    -0.07
    ofi
    -0.07
    okane
    -0.06
    ÑĨÑİ
    -0.06
    emente
    -0.06
    -Owned
    -0.06
    peon
    -0.06
    argest
    -0.06
     immigr
    -0.06
    POSITIVE LOGITS
    AFP
    0.09
     AFP
    0.09
     US
    0.07
    linked
    0.07
     -
    0.06
     "
    0.06
    oso
    0.06
    -linked
    0.06
     boosted
    0.06
     envis
    0.06
    Activations Density 0.039%

    No Known Activations