© 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. 29807
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "I" and its variations in different contexts

    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
    opak
    -0.07
    .EventQueue
    -0.07
    Ỽt
    -0.07
    vetica
    -0.07
    onta
    -0.07
    -<?
    -0.07
    omaly
    -0.07
    esco
    -0.07
    aeda
    -0.07
    ippy
    -0.07
    POSITIVE LOGITS
     Gand
    0.07
    lixir
    0.06
    å¬
    0.06
    177
    0.06
     inform
    0.06
    رÙĪÙĩ
    0.06
    leigh
    0.06
    outs
    0.06
    NAL
    0.05
    152
    0.05
    Activations Density 0.000%

    No Known Activations