© 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. 82885
    Prev
    Next
    INDEX
    Explanations

    references to visual representations or illustrations in the document

    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
    onga
    -0.07
    urd
    -0.06
    indow
    -0.06
    awi
    -0.06
    ongo
    -0.06
    935
    -0.06
    念
    -0.06
    Lite
    -0.05
    ampaign
    -0.05
    argins
    -0.05
    POSITIVE LOGITS
     view
    0.15
     views
    0.14
     Views
    0.12
    view
    0.12
     View
    0.11
    views
    0.11
     perspective
    0.11
    Views
    0.11
    View
    0.11
     shot
    0.10
    Activations Density 0.092%

    No Known Activations