© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104218
    Prev
    Next
    INDEX
    Explanations

    references to the name "Hudson" in various 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
    ãĥĨãĥ«
    -0.08
     hã
    -0.08
    445
    -0.08
    ger
    -0.08
    elman
    -0.07
    ustry
    -0.07
    hold
    -0.07
    gest
    -0.07
    fty
    -0.07
    AGR
    -0.07
    POSITIVE LOGITS
    ized
    0.08
    ite
    0.08
    ian
    0.07
    вÑĸлÑĮ
    0.07
    izing
    0.07
    oggle
    0.07
    omics
    0.07
    -bound
    0.07
     lo
    0.06
    dale
    0.06
    Activations Density 0.016%

    No Known Activations