© 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. 85159
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications related to data processing and algorithms

    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
    758
    -0.06
     inf
    -0.06
    hangi
    -0.06
     ere
    -0.06
    essler
    -0.06
     nep
    -0.06
    oka
    -0.06
    олож
    -0.06
    awan
    -0.06
    ottes
    -0.05
    POSITIVE LOGITS
     each
    0.16
    each
    0.15
    Each
    0.14
     Each
    0.14
    æ¯ı
    0.14
     EACH
    0.13
     ÙĦÙĥÙĦ
    0.13
     кажд
    0.13
     má»Ĺi
    0.13
     æ¯ı
    0.13
    Activations Density 0.140%

    No Known Activations