© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 130905
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or talking about various topics and experiences

    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
    unj
    -0.08
    оÑĢов
    -0.08
    elay
    -0.07
    atik
    -0.07
    ắt
    -0.07
    __[
    -0.07
    Ú¯ÙĪ
    -0.07
    âĢª
    -0.07
    oggler
    -0.07
    iç
    -0.07
    POSITIVE LOGITS
    unar
    0.08
    agh
    0.08
     a
    0.07
     versus
    0.06
     vest
    0.05
     FixedUpdate
    0.05
     irony
    0.05
    izio
    0.05
    !
    0.05
    iate
    0.05
    Activations Density 0.004%

    No Known Activations