© 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. 69824
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their roles

    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
    ates
    -0.08
    аÑĩе
    -0.07
    ¶Į
    -0.07
    .updateDynamic
    -0.07
    ATES
    -0.07
    (æ°´
    -0.07
     veto
    -0.07
    League
    -0.07
    é¾Ħ
    -0.07
    (æľĪ
    -0.06
    POSITIVE LOGITS
     contest
    0.08
     contests
    0.08
    Boundary
    0.08
     seat
    0.07
     Boundary
    0.07
    contest
    0.07
     MP
    0.06
    308
    0.06
     Benn
    0.06
     constituency
    0.06
    Activations Density 0.028%

    No Known Activations