© 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. 105384
    Prev
    Next
    INDEX
    Explanations

    references to observers and public opinions

    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
    947
    -0.08
    entina
    -0.07
    utex
    -0.07
    illet
    -0.07
    zia
    -0.07
    requencies
    -0.07
    phia
    -0.07
    ekim
    -0.07
    MMdd
    -0.07
    aim
    -0.07
    POSITIVE LOGITS
     say
    0.07
    olars
    0.06
     Cunningham
    0.06
    rod
    0.06
    538
    0.06
    ivo
    0.06
     argue
    0.06
     sdl
    0.06
     refer
    0.05
     Mercer
    0.05
    Activations Density 0.024%

    No Known Activations