© 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. 75445
    Prev
    Next
    INDEX
    Explanations

    themes related to societal issues and emotional experiences

    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
    raq
    -0.07
    anders
    -0.07
    esser
    -0.07
    ((__
    -0.07
    ians
    -0.06
    antas
    -0.06
    ürn
    -0.06
    ür
    -0.06
    ami
    -0.06
    usz
    -0.06
    POSITIVE LOGITS
    /Peak
    0.07
    rawl
    0.07
    aylight
    0.07
    ÙĨدگÛĮ
    0.07
    ForResource
    0.07
    eldom
    0.06
    benh
    0.06
    SError
    0.06
    clerosis
    0.06
    /Dk
    0.06
    Activations Density 0.083%

    No Known Activations