© 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. 42313
    Prev
    Next
    INDEX
    Explanations

    sections or references to articles and publications

    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
     Casc
    -0.08
    ago
    -0.07
    AGO
    -0.07
    ialis
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    onus
    -0.07
    ATUS
    -0.07
    iped
    -0.06
    åŁŁ
    -0.06
    ยม
    -0.06
    POSITIVE LOGITS
     related
    0.06
    lein
    0.06
     Related
    0.06
    egie
    0.06
     aday
    0.06
     Article
    0.06
     geopolitical
    0.06
    Adam
    0.06
     geopol
    0.06
     unconditional
    0.05
    Activations Density 0.001%

    No Known Activations