© 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 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. 87430
    Prev
    Next
    INDEX
    Explanations

    references to hemp and its related products

    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
    hood
    -0.08
    er
    -0.08
     knife
    -0.07
    deps
    -0.07
    pdata
    -0.07
    hf
    -0.06
    fox
    -0.06
    aris
    -0.06
    ربÙĩ
    -0.06
    åijĺ
    -0.06
    POSITIVE LOGITS
    seed
    0.08
    ÛĮ
    0.07
    stead
    0.07
    arkan
    0.07
    stalk
    0.07
    Northern
    0.07
     batchSize
    0.07
    -INF
    0.06
    rik
    0.06
     Northern
    0.06
    Activations Density 0.001%

    No Known Activations