© 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. 85241
    Prev
    Next
    INDEX
    Explanations

    items and features related to clothing and food

    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
    uppe
    -0.07
    uger
    -0.06
     joined
    -0.06
    ût
    -0.06
    lopedia
    -0.06
    thag
    -0.06
    omo
    -0.06
    uft
    -0.06
    orea
    -0.06
    clair
    -0.06
    POSITIVE LOGITS
    æĪĸ
    0.07
    à¹Ģà¸ŀล
    0.07
    æĪĸèĢħ
    0.06
    844
    0.06
    ÄĽ
    0.06
     æĪĸ
    0.06
    -notch
    0.06
     hoặc
    0.06
    apor
    0.06
    edReader
    0.06
    Activations Density 0.009%

    No Known Activations