© 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. 70230
    Prev
    Next
    INDEX
    Explanations

    declarations of programming constructs, such as classes and structs

    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
    asz
    -0.06
     Hab
    -0.06
    ï¼Ł↵↵
    -0.06
    assel
    -0.06
    don
    -0.06
    raft
    -0.06
    [section
    -0.06
    CAC
    -0.06
    hab
    -0.06
    ény
    -0.06
    POSITIVE LOGITS
    lek
    0.07
    .sap
    0.07
    idlo
    0.07
    okino
    0.06
    ulner
    0.06
    ipur
    0.06
    lator
    0.06
    ikal
    0.06
    097
    0.06
    ä¼¼çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations