© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82302
    Prev
    Next
    INDEX
    Explanations

    terms related to art, design, and creativity

    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
    ÐĶÐļ
    -0.08
    ÙĥÙĬÙĦ
    -0.07
    á»iji
    -0.07
     Ngh
    -0.07
     cán
    -0.06
    .uk
    -0.06
    ÙĨÚ¯ÛĮ
    -0.06
    aload
    -0.06
    ัà¸įà¸į
    -0.06
    omanip
    -0.06
    POSITIVE LOGITS
    374
    0.06
    agon
    0.06
    bern
    0.06
     Atl
    0.06
    onom
    0.06
    üssen
    0.06
    atro
    0.06
    ishing
    0.06
    orget
    0.06
     Caucas
    0.06
    Activations Density 0.001%

    No Known Activations