© 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. 40488
    Prev
    Next
    INDEX
    Explanations

    governmental and administrative terms and roles

    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
    ffee
    -0.09
     fitte
    -0.09
     konkrét
    -0.09
    ollen
    -0.09
    ạc
    -0.09
     eskort
    -0.08
    GenerationStrategy
    -0.08
    >NN
    -0.08
    resi
    -0.08
     поглÑıд
    -0.08
    POSITIVE LOGITS
     d
    0.06
    arius
    0.06
     er
    0.06
     revis
    0.06
    0.06
     (
    0.06
     u
    0.05
     h
    0.05
     format
    0.05
     increasingly
    0.05
    Activations Density 0.017%

    No Known Activations