© 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. 9-LLAMASCOPE-RES-131K
    11. 98818
    Prev
    Next
    INDEX
    Explanations

    references to political parties, particularly in an Italian context

    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
    enant
    -0.09
    crete
    -0.07
    .VK
    -0.07
    еÑĢп
    -0.07
    ogn
    -0.07
    ronym
    -0.06
    acz
    -0.06
     fur
    -0.06
    elp
    -0.06
    ambi
    -0.06
    POSITIVE LOGITS
    onis
    0.06
     cracks
    0.06
    à¸ķร
    0.06
    urve
    0.06
    381
    0.06
     abnormal
    0.06
     Abraham
    0.06
    lam
    0.06
     Neal
    0.06
     Kun
    0.05
    Activations Density 0.000%

    No Known Activations