© 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. 9-LLAMASCOPE-RES-131K
    11. 96326
    Prev
    Next
    INDEX
    Explanations

    textual elements that define or interpret the meaning of words and phrases

    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
     Pill
    -0.07
    usk
    -0.07
    ior
    -0.07
    796
    -0.06
    965
    -0.06
    apper
    -0.06
    azu
    -0.06
    que
    -0.06
    æľį
    -0.06
    orte
    -0.06
    POSITIVE LOGITS
    .openg
    0.07
    _iff
    0.07
    ÙijÙĩ
    0.07
    κÏģι
    0.07
    ůl
    0.07
    ÑĢаÑģÑĤ
    0.06
     [](
    0.06
    etÃŃ
    0.06
    ccione
    0.06
     æĬķ稿
    0.06
    Activations Density 0.009%

    No Known Activations