© 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. 81562
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and roles

    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
     hei
    -0.09
    erti
    -0.08
    òi
    -0.08
     McCart
    -0.08
    egen
    -0.08
    anded
    -0.08
    bÃŃr
    -0.08
    //{{
    -0.07
    Streamer
    -0.07
    edn
    -0.07
    POSITIVE LOGITS
    _stdout
    0.07
     closest
    0.06
     en
    0.06
     ideal
    0.06
     chosen
    0.06
     partner
    0.05
    é¾
    0.05
    ãĥ¡ãĥªãĤ«
    0.05
     intens
    0.05
     base
    0.05
    Activations Density 0.009%

    No Known Activations