© 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. 105831
    Prev
    Next
    INDEX
    Explanations

    references to issues or factors related to involvement or participation

    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
     Ult
    -0.07
    gon
    -0.07
    /repository
    -0.06
    vit
    -0.06
    fasta
    -0.06
    PyObject
    -0.06
    ippers
    -0.06
    è¼
    -0.06
     inclusion
    -0.06
    ulia
    -0.06
    POSITIVE LOGITS
    artner
    0.07
    hek
    0.07
    θÏħ
    0.06
    rys
    0.06
    egen
    0.06
    oyer
    0.06
    kom
    0.06
    ahat
    0.06
    leen
    0.06
    hoot
    0.06
    Activations Density 0.006%

    No Known Activations