© 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. 76627
    Prev
    Next
    INDEX
    Explanations

    references to pregnancy and fetal development

    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
     ej
    -0.06
    resa
    -0.06
     affairs
    -0.06
    conds
    -0.05
    ä¸Ī
    -0.05
    .mdl
    -0.05
     Hlav
    -0.05
     ne
    -0.05
    .circular
    -0.05
    enko
    -0.05
    POSITIVE LOGITS
    omentum
    0.07
    him
    0.07
    oot
    0.07
     vá»ĭ
    0.07
    OCUMENT
    0.07
    _detach
    0.06
    uiten
    0.06
    à¸
    0.06
    ģn
    0.06
    489
    0.06
    Activations Density 0.011%

    No Known Activations