© 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. 75996
    Prev
    Next
    INDEX
    Explanations

    instances of cause and effect reasoning or explanations

    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
    shi
    -0.07
    ĮĢ
    -0.06
     PyErr
    -0.06
    маз
    -0.06
    DSL
    -0.06
    pong
    -0.06
    ock
    -0.06
    ichert
    -0.06
     Lamp
    -0.06
    âĻª
    -0.06
    POSITIVE LOGITS
     because
    0.17
    because
    0.15
     Because
    0.14
     porque
    0.14
    Because
    0.13
     omdat
    0.13
    åĽłä¸º
    0.13
     karena
    0.12
    ecause
    0.12
     weil
    0.12
    Activations Density 0.034%

    No Known Activations