© 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 EvalsExportsinterp-engineNEWAPI 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. 124074
    Prev
    Next
    INDEX
    Explanations

    references to the separation of immigrant families

    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
    ãĤīãģĽ
    -0.07
    oload
    -0.07
    alars
    -0.07
    /Images
    -0.07
    dez
    -0.07
    ASM
    -0.07
    anders
    -0.07
    ÙħÙĪ
    -0.07
    anan
    -0.06
    athing
    -0.06
    POSITIVE LOGITS
     separ
    0.17
     separation
    0.17
     separated
    0.16
     Separ
    0.15
     separating
    0.14
    -separated
    0.13
     separates
    0.13
    Separ
    0.12
    Separated
    0.12
     split
    0.11
    Activations Density 0.077%

    No Known Activations