© 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. 85191
    Prev
    Next
    INDEX
    Explanations

    references to the term "Lex" or related keywords

    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
    .wp
    -0.07
    rob
    -0.07
    atten
    -0.07
    bus
    -0.07
    bed
    -0.07
    adder
    -0.06
    .DEFINE
    -0.06
    ptive
    -0.06
    fon
    -0.06
    udad
    -0.06
    POSITIVE LOGITS
    ical
    0.09
    ington
    0.08
    eker
    0.08
    eme
    0.08
    iles
    0.07
    ible
    0.07
    icons
    0.07
    cellent
    0.07
    mate
    0.07
    icon
    0.07
    Activations Density 0.012%

    No Known Activations