© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    concepts related to discovery and connection in various forms

    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
     zav
    -0.08
     siti
    -0.07
    arent
    -0.06
    utsch
    -0.06
    横
    -0.06
     Rip
    -0.06
    ocz
    -0.06
    aint
    -0.06
     okol
    -0.06
    ắc
    -0.06
    POSITIVE LOGITS
     relief
    0.08
    ered
    0.08
     peace
    0.07
    Kn
    0.07
     inspiration
    0.07
     strength
    0.07
     success
    0.07
     balance
    0.07
     himself
    0.07
     ANSW
    0.07
    Activations Density 0.020%

    No Known Activations