© 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. 108493
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming and control structures

    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
    _utilities
    -0.08
    .scalablytyped
    -0.08
    cctor
    -0.08
    oggles
    -0.07
    èģĺ
    -0.07
    LinkId
    -0.07
    imler
    -0.07
    esson
    -0.07
    _TOGGLE
    -0.07
    agus
    -0.07
    POSITIVE LOGITS
     support
    0.09
     ability
    0.08
     capability
    0.08
     experimental
    0.08
    able
    0.07
     features
    0.07
     feature
    0.07
     use
    0.07
     facility
    0.07
    FEATURE
    0.07
    Activations Density 0.104%

    No Known Activations