© 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. 75015
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes of beverages, specifically focusing on flavor and quality characteristics

    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
    hart
    -0.07
     Jew
    -0.07
    istros
    -0.07
    serie
    -0.06
    weep
    -0.06
    ãĥĭãĥ¼
    -0.06
    artz
    -0.06
    eries
    -0.06
    witch
    -0.06
     witch
    -0.06
    POSITIVE LOGITS
    TD
    0.07
    dle
    0.07
     Huffman
    0.06
    ("`
    0.06
    alah
    0.06
     aging
    0.06
    bil
    0.06
    ãĥ¼ãĥĵ
    0.06
    ogene
    0.06
     complex
    0.06
    Activations Density 0.003%

    No Known Activations