© 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. 89416
    Prev
    Next
    INDEX
    Explanations

    web addresses or URLs

    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
     possible
    -0.06
     CircularProgress
    -0.06
    åŀ
    -0.05
    388
    -0.05
    <decltype
    -0.05
     ph
    -0.05
    ian
    -0.05
    بÙĪر
    -0.05
    werp
    -0.05
     borrowing
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.07
    eyse
    0.07
    925
    0.07
    .gameserver
    0.07
    ordum
    0.07
     Hoch
    0.07
    enco
    0.07
    ģn
    0.07
    ENN
    0.06
    buz
    0.06
    Activations Density 0.001%

    No Known Activations