© 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. 127462
    Prev
    Next
    INDEX
    Explanations

    commands or prompts for content manipulation or visibility

    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
    andre
    -0.07
    zdy
    -0.07
    ves
    -0.06
    iffin
    -0.06
    dbo
    -0.06
    anas
    -0.06
    ving
    -0.06
    enes
    -0.06
    pto
    -0.06
    ven
    -0.06
    POSITIVE LOGITS
    pread
    0.06
    enville
    0.06
    ackbar
    0.06
    initializer
    0.06
    baum
    0.06
    usement
    0.06
    enders
    0.06
    ipur
    0.06
    Äįné
    0.06
    bakan
    0.06
    Activations Density 0.000%

    No Known Activations