© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74322
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values or identifiers

    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
    apt
    -0.09
    opia
    -0.08
    ues
    -0.07
    olo
    -0.07
    elib
    -0.07
    immer
    -0.07
    utan
    -0.07
    yla
    -0.07
    igo
    -0.07
    ongo
    -0.07
    POSITIVE LOGITS
    hoff
    0.07
    -sama
    0.07
     UsersController
    0.07
     PartialView
    0.07
    Ø©
    0.06
    eza
    0.06
    igrations
    0.06
    cheng
    0.06
    itored
    0.06
    Ñĥла
    0.06
    Activations Density 0.011%

    No Known Activations