© 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. 120577
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mun" along with variations of it

    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
    lette
    -0.06
    589
    -0.06
    ders
    -0.06
    dust
    -0.06
    .flash
    -0.06
    versible
    -0.06
    екÑĤ
    -0.06
    585
    -0.06
    風
    -0.06
    intosh
    -0.06
    POSITIVE LOGITS
    roe
    0.10
    ammad
    0.07
    STER
    0.07
    nero
    0.07
    tering
    0.07
    erator
    0.06
    ster
    0.06
     Mouth
    0.06
    ally
    0.06
    tep
    0.06
    Activations Density 0.006%

    No Known Activations