© 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 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. 40520
    Prev
    Next
    INDEX
    Explanations

    occurrences of curly braces in mathematical or scientific expressions

    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
    inclu
    -0.08
    atica
    -0.08
    usi
    -0.08
     Král
    -0.07
     Ekon
    -0.07
    owie
    -0.07
    eah
    -0.07
    TRL
    -0.07
    ledon
    -0.07
    .д
    -0.07
    POSITIVE LOGITS
     McDon
    0.06
    elves
    0.06
    lant
    0.05
    onta
    0.05
     Lite
    0.05
    _medium
    0.05
    bsite
    0.05
     java
    0.05
     lint
    0.05
    cola
    0.05
    Activations Density 0.004%

    No Known Activations