© 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. 81704
    Prev
    Next
    INDEX
    Explanations

    patterns in numerical or coded formats

    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
    odore
    -0.08
    anim
    -0.07
    ople
    -0.07
    illery
    -0.07
    xn
    -0.07
    umas
    -0.06
     Hra
    -0.06
    ieren
    -0.06
    ARING
    -0.06
    ners
    -0.06
    POSITIVE LOGITS
     بÙĪابة
    0.07
    ecko
    0.07
    VRT
    0.07
    //*
    0.07
    isque
    0.06
    shr
    0.06
     ki
    0.06
    ä½
    0.06
    zl
    0.06
     isp
    0.06
    Activations Density 0.022%

    No Known Activations