© 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 EvalsExportsinterp-engineNEWAPI 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. 17796
    Prev
    Next
    INDEX
    Explanations

    components and classes related to buttons and navigation in web design

    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
    andest
    -0.07
    rupt
    -0.06
    licas
    -0.06
     Å¡t
    -0.06
    enburg
    -0.06
    ums
    -0.06
    indir
    -0.06
    ept
    -0.06
    ries
    -0.06
    бÑĥÑĢг
    -0.06
    POSITIVE LOGITS
    orio
    0.06
    xA
    0.06
    Persistence
    0.06
    anza
    0.06
    OS
    0.06
    üf
    0.06
     sul
    0.06
    ror
    0.06
    ena
    0.06
    âĺħâĺħ
    0.06
    Activations Density 0.003%

    No Known Activations