© 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. 95442
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant or impactful events or phrases

    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
    pins
    -0.07
    ÙĪتÛĮ
    -0.06
    olini
    -0.06
    دار
    -0.06
    anel
    -0.06
    kara
    -0.06
    ·
    -0.06
    pin
    -0.06
    inst
    -0.06
    idebar
    -0.06
    POSITIVE LOGITS
    wang
    0.07
    (æľ¨
    0.07
     @[
    0.07
    .Rollback
    0.06
    eneg
    0.06
    :č↵č↵
    0.06
    ãi
    0.06
     grav
    0.06
    ÏģοÏħ
    0.06
     Arbitrary
    0.06
    Activations Density 0.004%

    No Known Activations