© 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 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. 59294
    Prev
    Next
    INDEX
    Explanations

    numerical values related to age or statistics in obituaries

    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
    á»įt
    -0.06
    hurst
    -0.06
    ifton
    -0.06
     pii
    -0.06
    .fm
    -0.06
     Deniz
    -0.06
    ÑĦи
    -0.06
    abor
    -0.06
    enge
    -0.06
    ampton
    -0.05
    POSITIVE LOGITS
    elman
    0.07
    celed
    0.07
    ean
    0.06
    ickers
    0.06
    elts
    0.06
    ÐŁÐļ
    0.06
    FLAGS
    0.06
    åīĽ
    0.06
    _itr
    0.06
    asInstanceOf
    0.06
    Activations Density 0.005%

    No Known Activations