© 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. 95793
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical dimensions and their representations

    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
    लत
    -0.07
    azu
    -0.07
     Äij
    -0.07
    urd
    -0.07
    edBy
    -0.07
    usch
    -0.06
    à¥ĩण
    -0.06
    ازÛĮ
    -0.06
    ož
    -0.06
    adlo
    -0.06
    POSITIVE LOGITS
     alike
    0.17
     respectively
    0.12
     ÑģооÑĤвеÑĤ
    0.06
     respective
    0.06
    à¹Ħล
    0.06
    depending
    0.06
     Pou
    0.06
     Jer
    0.06
     gren
    0.06
    ubar
    0.06
    Activations Density 0.097%

    No Known Activations