© 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. 30968
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific place names

    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
     Bul
    -0.08
     Armour
    -0.07
    æĺĩ
    -0.06
    èIJ½ãģ¡
    -0.06
    aukee
    -0.06
     promin
    -0.06
    oger
    -0.06
    att
    -0.06
     aalborg
    -0.06
    846
    -0.06
    POSITIVE LOGITS
     isolate
    0.09
     primitives
    0.08
     contact
    0.07
     kontakt
    0.07
     isolated
    0.07
    /proto
    0.07
     isolation
    0.07
     world
    0.07
    isol
    0.07
     isol
    0.07
    Activations Density 0.003%

    No Known Activations