© 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. 92917
    Prev
    Next
    INDEX
    Explanations

    numerical data and code-like structures

    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
    odyn
    -0.07
    ieval
    -0.07
    ikh
    -0.06
    ún
    -0.06
    imler
    -0.06
    imary
    -0.06
     Bram
    -0.06
    ules
    -0.06
    iences
    -0.06
    iode
    -0.06
    POSITIVE LOGITS
     McInt
    0.07
    оÑģÑĤи
    0.06
    emachine
    0.06
    elli
    0.06
    .lang
    0.06
     Boyd
    0.06
     Wik
    0.06
    اÙĥ
    0.06
     Received
    0.06
     Rut
    0.05
    Activations Density 0.011%

    No Known Activations