© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 27572
    Prev
    Next
    INDEX
    Explanations

    references to political elections and candidates

    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
    CompleteListener
    -0.07
    etsy
    -0.06
     Budget
    -0.06
    thouse
    -0.06
    θεÏģ
    -0.06
    Sensitive
    -0.06
    ÑĢади
    -0.06
    ogle
    -0.06
    xo
    -0.06
    Budget
    -0.06
    POSITIVE LOGITS
     primary
    0.08
     party
    0.07
    -primary
    0.07
     PRIMARY
    0.07
    åħļ
    0.06
     Primary
    0.06
     Party
    0.06
     delegates
    0.06
     selection
    0.06
     leadership
    0.06
    Activations Density 0.023%

    No Known Activations