© 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. 3629
    Prev
    Next
    INDEX
    Explanations

    references to family lineage and heritage

    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
    jab
    -0.07
    uem
    -0.06
     vent
    -0.06
     Hoff
    -0.06
    ridden
    -0.06
    uit
    -0.06
     insign
    -0.06
    inet
    -0.06
    uir
    -0.06
     Fade
    -0.06
    POSITIVE LOGITS
     side
    0.17
    -side
    0.16
     Side
    0.15
    _side
    0.15
    Side
    0.15
    åģ´
    0.14
    side
    0.14
     côté
    0.13
     sides
    0.13
     lado
    0.13
    Activations Density 0.064%

    No Known Activations