© 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. 17-LLAMASCOPE-RES-131K
    6. 59577
    Prev
    Next
    INDEX
    Explanations

    names, particularly those with the syllable "err" and variations thereof

    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
    gere
    -0.10
    ed
    -0.09
    edii
    -0.08
    elow
    -0.07
    iating
    -0.07
     onDataChange
    -0.07
    -liter
    -0.07
    liter
    -0.07
    //{{
    -0.07
    reeNode
    -0.07
    POSITIVE LOGITS
    ington
    0.09
    icle
    0.07
    न
    0.07
    æľµ
    0.07
    inja
    0.07
    one
    0.07
    eri
    0.07
    ainer
    0.07
    issen
    0.07
    uss
    0.07
    Activations Density 0.015%

    No Known Activations