© 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. 87847
    Prev
    Next
    INDEX
    Explanations

    references to family and their emotional responses

    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
    ARSER
    -0.07
    íĥĦ
    -0.06
    escape
    -0.06
    <?,
    -0.06
    ectar
    -0.06
    .escape
    -0.06
    åĽ
    -0.06
    uldu
    -0.06
     Swe
    -0.06
    ény
    -0.06
    POSITIVE LOGITS
    ogy
    0.07
    ĶåĽŀ
    0.07
    'gc
    0.06
    ustil
    0.06
     privacy
    0.06
    ุส
    0.06
    èħIJ
    0.06
     vig
    0.06
     Raymond
    0.06
     Coch
    0.06
    Activations Density 0.023%

    No Known Activations