© 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. 73566
    Prev
    Next
    INDEX
    Explanations

    various types of flooring and construction terminology

    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
    èī¦
    -0.06
    ence
    -0.06
     Alexand
    -0.06
    599
    -0.06
    inerary
    -0.06
    -regexp
    -0.05
     chops
    -0.05
    ouden
    -0.05
    anje
    -0.05
    649
    -0.05
    POSITIVE LOGITS
     modular
    0.07
     kit
    0.07
     assembly
    0.07
     INST
    0.07
     interchange
    0.07
     assembling
    0.06
     Fam
    0.06
     assemble
    0.06
    Ñıж
    0.06
     preload
    0.06
    Activations Density 0.002%

    No Known Activations