© 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. 73108
    Prev
    Next
    INDEX
    Explanations

    references to alcoholic beverages and drinks

    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
    ema
    -0.06
    iest
    -0.06
     hum
    -0.06
    .cfg
    -0.06
    eling
    -0.06
    eper
    -0.06
    emas
    -0.06
    ãĤ¢ãĥ¼
    -0.06
    495
    -0.06
    ched
    -0.06
    POSITIVE LOGITS
    /gin
    0.07
    esModule
    0.07
    abinet
    0.06
    enburg
    0.06
    Äħż
    0.06
    VERTISEMENT
    0.06
    शन
    0.06
    ibs
    0.06
     ÙħاÛĮÙĦ
    0.06
     served
    0.06
    Activations Density 0.024%

    No Known Activations