© 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. 17-LLAMASCOPE-RES-131K
    11. 77858
    Prev
    Next
    INDEX
    Explanations

    references to specific landmarks or locations

    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
     Lod
    -0.06
    ÑĢаг
    -0.06
    679
    -0.06
    rapper
    -0.05
    uge
    -0.05
     Walsh
    -0.05
    ãģ
    -0.05
     Stim
    -0.05
    aste
    -0.05
     calendar
    -0.05
    POSITIVE LOGITS
    ervas
    0.08
    iland
    0.07
    inand
    0.07
    WithOptions
    0.07
    edriver
    0.07
    entr
    0.07
    avicon
    0.07
     tô
    0.07
    coni
    0.07
    AGO
    0.06
    Activations Density 0.000%

    No Known Activations