© 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. 9-LLAMASCOPE-RES-131K
    11. 95202
    Prev
    Next
    INDEX
    Explanations

    references to specific events or dates

    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
    оÑĢдин
    -0.09
    िà¤ķत
    -0.07
    ICI
    -0.07
    etta
    -0.07
    ikk
    -0.06
    ici
    -0.06
     Inches
    -0.06
    icl
    -0.06
    elper
    -0.06
    stairs
    -0.06
    POSITIVE LOGITS
     Dit
    0.07
    alue
    0.06
     pare
    0.06
     aff
    0.06
    emiz
    0.06
    metro
    0.06
    sense
    0.06
     Pul
    0.06
     quint
    0.06
    eczy
    0.06
    Activations Density 0.009%

    No Known Activations