© 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. 1445
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or structural elements in documents

    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
    ¢åįķ
    -0.08
    wner
    -0.07
    ionale
    -0.07
    WidgetItem
    -0.07
    zano
    -0.07
    icode
    -0.07
    caffold
    -0.07
    éĢ¸
    -0.07
    ometr
    -0.07
    ège
    -0.07
    POSITIVE LOGITS
    ancia
    0.06
     Barg
    0.06
    íijľ
    0.06
    BBBB
    0.06
     Rory
    0.06
    rippling
    0.05
    %S
    0.05
    lings
    0.05
     sem
    0.05
    ened
    0.05
    Activations Density 0.000%

    No Known Activations