© 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. 29954
    Prev
    Next
    INDEX
    Explanations

    actions related to announcements and changes in business and industry practices

    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
    æł¸
    -0.07
    Ł
    -0.07
    æĺ¯ä¸Ģ个
    -0.06
     zor
    -0.06
    ita
    -0.06
    odcast
    -0.06
    emand
    -0.06
     someone
    -0.06
    iez
    -0.06
    itta
    -0.06
    POSITIVE LOGITS
     themselves
    0.14
     their
    0.12
    their
    0.11
    Their
    0.10
     either
    0.10
     leurs
    0.10
    Either
    0.10
    either
    0.09
     ihren
    0.09
     respective
    0.09
    Activations Density 0.054%

    No Known Activations