© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103420
    Prev
    Next
    INDEX
    Explanations

    programming commands and annotations related to event handling and configuration

    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
     Glas
    -0.07
     αδ
    -0.06
    .yy
    -0.06
    289
    -0.06
     charg
    -0.06
    нин
    -0.06
    idor
    -0.06
    adol
    -0.06
    ó
    -0.06
    oyer
    -0.06
    POSITIVE LOGITS
    anki
    0.07
    icum
    0.06
     {{{
    0.06
    oreach
    0.06
    avn
    0.06
    گاÙĨÛĮ
    0.06
     Pocket
    0.06
     reap
    0.05
    ÛĮÙĩ
    0.05
     Tablet
    0.05
    Activations Density 0.058%

    No Known Activations