© 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. 93957
    Prev
    Next
    INDEX
    Explanations

    references to optional features or configurations in technology-related discussions

    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
    oplevel
    -0.08
    akest
    -0.07
    .must
    -0.07
    illet
    -0.07
    IPA
    -0.07
     każ
    -0.07
    nga
    -0.06
    _marshall
    -0.06
     everybody
    -0.06
    ãģĿãģĹãģ¦
    -0.06
    POSITIVE LOGITS
     other
    0.13
     additional
    0.13
     further
    0.10
    additional
    0.10
    other
    0.10
     additionally
    0.10
     Additional
    0.09
     thêm
    0.09
    Additional
    0.09
    åħ¶ä»ĸ
    0.09
    Activations Density 0.059%

    No Known Activations