© 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. 105852
    Prev
    Next
    INDEX
    Explanations

    references to data visualization libraries and their functionalities

    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
    ahn
    -0.07
     Meg
    -0.06
    é¦
    -0.06
     FML
    -0.06
     Urb
    -0.06
    radius
    -0.06
     Pony
    -0.06
    LR
    -0.05
    çon
    -0.05
     Newport
    -0.05
    POSITIVE LOGITS
     Harlem
    0.08
    uster
    0.07
     Rochester
    0.07
     DevExpress
    0.07
    beros
    0.07
    #
    0.07
    annabin
    0.07
     YORK
    0.07
     Cuomo
    0.07
    USTER
    0.07
    Activations Density 0.007%

    No Known Activations