© 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. 86364
    Prev
    Next
    INDEX
    Explanations

    references to companies and economic entities associated with Ukraine

    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
    .mx
    -0.08
    PÅĻÃŃ
    -0.07
    fetchAll
    -0.07
     Labrador
    -0.07
    %%%%%%%%%%%%%%%%
    -0.06
    bjerg
    -0.06
    otton
    -0.06
     Äįe
    -0.06
    uckland
    -0.06
    ÎĨ
    -0.06
    POSITIVE LOGITS
     Ukraine
    0.14
     Ukrainian
    0.13
     Ukrain
    0.12
     Kiev
    0.11
     Ukr
    0.11
     Baltimore
    0.11
     Maryland
    0.10
     Lv
    0.10
     УкÑĢа
    0.10
     Ukraj
    0.10
    Activations Density 0.046%

    No Known Activations