© 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. 124017
    Prev
    Next
    INDEX
    Explanations

    ingredients and processes involved in cooking and baking

    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
    Glass
    -0.06
     Glass
    -0.06
     glass
    -0.06
     closure
    -0.06
    dance
    -0.06
     Closure
    -0.06
    bucket
    -0.06
     susp
    -0.06
    ystem
    -0.06
     System
    -0.05
    POSITIVE LOGITS
    ková
    0.08
     wax
    0.08
     blocks
    0.08
     block
    0.08
    åĿĹ
    0.08
    SION
    0.07
    block
    0.07
     Blocks
    0.07
     compact
    0.07
    .pb
    0.07
    Activations Density 0.045%

    No Known Activations