© 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. 5520
    Prev
    Next
    INDEX
    Explanations

    instructions and considerations related to preparation and cooking

    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
    éĩĩ
    -0.06
     .
    -0.06
     success
    -0.06
     Kak
    -0.05
     dot
    -0.05
     rack
    -0.05
     progress
    -0.05
     full
    -0.05
     under
    -0.05
     demand
    -0.05
    POSITIVE LOGITS
    .EntityFramework
    0.07
    è£ģ
    0.07
     Evel
    0.07
    .ends
    0.07
     éĤ
    0.07
    #ac
    0.07
    ende
    0.07
    :uint
    0.07
    EndPoint
    0.07
    ToFit
    0.06
    Activations Density 0.008%

    No Known Activations