© 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. 126755
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "get."

    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
    enal
    -0.07
    arl
    -0.07
    quito
    -0.06
    nal
    -0.06
    rrha
    -0.06
    -CP
    -0.06
    ifen
    -0.06
    jak
    -0.06
    keit
    -0.06
    kea
    -0.06
    POSITIVE LOGITS
    chas
    0.08
    è¿«
    0.06
    باÙĨ
    0.06
    è£ħç½®
    0.06
    OrElse
    0.06
    cher
    0.06
    OMEM
    0.06
    enda
    0.06
    WithContext
    0.06
    imate
    0.06
    Activations Density 0.015%

    No Known Activations