© 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. 17527
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and attributes

    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
    abbr
    -0.08
    asio
    -0.08
    Transmission
    -0.07
    Hostname
    -0.06
    _LAYER
    -0.06
     باب
    -0.06
    õi
    -0.06
    utherford
    -0.06
     Elephant
    -0.06
     Transmission
    -0.06
    POSITIVE LOGITS
     Entries
    0.06
    Entry
    0.06
    .learn
    0.06
     Industries
    0.06
     entries
    0.06
    âīł
    0.06
    esis
    0.06
    umber
    0.06
     entry
    0.06
    ller
    0.06
    Activations Density 0.008%

    No Known Activations