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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84140
    Prev
    Next
    INDEX
    Explanations

    references to product launches and specifications in technology announcements

    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
    conciliation
    -0.07
    inson
    -0.07
    rollo
    -0.07
     tutorials
    -0.07
    çĵ¶
    -0.07
     MessageBoxIcon
    -0.06
    NodeId
    -0.06
    ãĥ³ãĥĩ
    -0.06
    KeyType
    -0.06
    ideographic
    -0.06
    POSITIVE LOGITS
     products
    0.10
     product
    0.07
    products
    0.07
    elen
    0.07
     new
    0.06
     smallest
    0.06
     Products
    0.06
     Produkte
    0.06
     killer
    0.06
     preview
    0.06
    Activations Density 0.015%

    No Known Activations