© 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. 75793
    Prev
    Next
    INDEX
    Explanations

    technical terms and advice related to medical or nutritional supplements

    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
     Seal
    -0.06
    emento
    -0.06
    agen
    -0.06
     å¾Ĺ
    -0.06
    afb
    -0.06
    gis
    -0.06
     çī
    -0.06
    iffer
    -0.06
    bridge
    -0.06
    عÛĮ
    -0.06
    POSITIVE LOGITS
     preferred
    0.12
     preference
    0.12
    preferred
    0.11
     exclusively
    0.10
    Preferred
    0.10
     exclusive
    0.10
     prefer
    0.10
     tercih
    0.10
     Preferred
    0.09
     пÑĢедпоÑĩ
    0.09
    Activations Density 0.100%

    No Known Activations