© 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. 124375
    Prev
    Next
    INDEX
    Explanations

    references to data structures and components in programming or software development

    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
    ickets
    -0.08
    urette
    -0.08
    еÑĤе
    -0.07
    SingleNode
    -0.07
     Hide
    -0.06
    nze
    -0.06
    nEnter
    -0.06
    .desktop
    -0.06
     Chairs
    -0.06
    GenerationStrategy
    -0.06
    POSITIVE LOGITS
     list
    0.10
    list
    0.07
    ardy
    0.07
    .lst
    0.06
     roster
    0.06
     kitty
    0.06
    åĥķ
    0.06
     List
    0.06
     collection
    0.06
    elist
    0.06
    Activations Density 0.033%

    No Known Activations