© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90706
    Prev
    Next
    INDEX
    Explanations

    locations and geographic references 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
    /Foundation
    -0.07
    AXB
    -0.07
    phans
    -0.07
    ë¹Ļ
    -0.06
    tega
    -0.06
    åŁ
    -0.06
    dehy
    -0.06
    angelog
    -0.06
    elon
    -0.06
    .Dto
    -0.06
    POSITIVE LOGITS
     CoreData
    0.07
     célib
    0.07
    /browse
    0.06
    ika
    0.06
    zcze
    0.06
     Tracy
    0.06
    /copyleft
    0.06
    IFY
    0.06
     Trait
    0.06
    itia
    0.06
    Activations Density 0.016%

    No Known Activations