© 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. 72387
    Prev
    Next
    INDEX
    Explanations

    biblical references and quotations

    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
    -rule
    -0.07
    stal
    -0.07
    aghan
    -0.07
    abama
    -0.07
    rule
    -0.07
     Rule
    -0.07
    kening
    -0.07
    리ìĸ´
    -0.07
    ä¾
    -0.06
    è£Ĥ
    -0.06
    POSITIVE LOGITS
    jos
    0.06
    ikk
    0.06
    idle
    0.06
    .om
    0.06
     compass
    0.06
    abcdefghijkl
    0.06
    685
    0.06
    νοÏį
    0.06
    ichi
    0.06
     Uns
    0.05
    Activations Density 0.018%

    No Known Activations