© 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. 15-LLAMASCOPE-RES-131K
    11. 103483
    Prev
    Next
    INDEX
    Explanations

    question marks and their context in a text

    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
    cis
    -0.07
    REP
    -0.06
    ogen
    -0.06
     compartment
    -0.06
    pond
    -0.06
    .ci
    -0.06
    ies
    -0.06
    trait
    -0.05
    ocos
    -0.05
     Bauer
    -0.05
    POSITIVE LOGITS
    .cx
    0.07
    ERVED
    0.07
    ouz
    0.07
    üs
    0.07
    ĵåIJį
    0.06
    =read
    0.06
     erotik
    0.06
    ioxide
    0.06
    -orders
    0.06
     Orders
    0.06
    Activations Density 0.001%

    No Known Activations