© 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. 15-LLAMASCOPE-RES-131K
    11. 88118
    Prev
    Next
    INDEX
    Explanations

    references to children or child-related demographics

    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
    .ov
    -0.07
    abyrin
    -0.07
    lector
    -0.07
    ulis
    -0.07
    anka
    -0.07
    wal
    -0.07
    erif
    -0.07
    ubern
    -0.06
    xFFF
    -0.06
    eut
    -0.06
    POSITIVE LOGITS
    æīĺ
    0.06
     Wheeler
    0.06
     analog
    0.06
    419
    0.06
     Vance
    0.06
    ansion
    0.05
    259
    0.05
    iez
    0.05
    615
    0.05
    732
    0.05
    Activations Density 0.000%

    No Known Activations