© 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. 17-LLAMASCOPE-RES-131K
    11. 39754
    Prev
    Next
    INDEX
    Explanations

    references to British Columbia and its legal or environmental matters

    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
    usher
    -0.07
    ocrat
    -0.07
    enger
    -0.07
    INGER
    -0.07
    ament
    -0.07
    uns
    -0.07
    oon
    -0.07
    oval
    -0.07
    ackbar
    -0.07
    unta
    -0.07
    POSITIVE LOGITS
    rypted
    0.07
    -wide
    0.07
    èī
    0.07
    (PC
    0.06
    "<?
    0.06
    itters
    0.06
    isson
    0.06
    adia
    0.06
    нки
    0.06
    sku
    0.06
    Activations Density 0.009%

    No Known Activations