© 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. 9-LLAMASCOPE-RES-131K
    11. 98518
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "OMG."

    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
    anda
    -0.06
    ellen
    -0.06
     ex
    -0.06
     oc
    -0.06
     rem
    -0.06
    591
    -0.06
    apo
    -0.06
    la
    -0.05
    erken
    -0.05
     upper
    -0.05
    POSITIVE LOGITS
    TEE
    0.07
    ÙĤب
    0.07
    jour
    0.07
    menin
    0.07
    itzer
    0.07
    ignet
    0.07
    wor
    0.07
    anness
    0.06
    .locale
    0.06
    vious
    0.06
    Activations Density 0.000%

    No Known Activations