© 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. 5-LLAMASCOPE-RES-131K
    11. 125492
    Prev
    Next
    INDEX
    Explanations

    terms related to ancient Egyptian writing and script types

    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
    elib
    -0.09
    elight
    -0.07
    elong
    -0.07
    itel
    -0.07
    bern
    -0.07
    foy
    -0.06
    aliases
    -0.06
    uliar
    -0.06
    anten
    -0.06
    strict
    -0.06
    POSITIVE LOGITS
    rans
    0.07
    ุà¸ķ
    0.06
     Rams
    0.06
    tam
    0.06
    INVAL
    0.06
     RAM
    0.06
    eza
    0.06
     Horm
    0.06
     wr
    0.06
    ISTA
    0.06
    Activations Density 0.027%

    No Known Activations