© 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. 57938
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and specific titles

    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
    ka
    -0.14
    li
    -0.11
    che
    -0.11
    nya
    -0.11
    bo
    -0.10
    pro
    -0.10
    ben
    -0.10
    tr
    -0.10
    bes
    -0.10
    be
    -0.10
    POSITIVE LOGITS
    Ùĭ
    0.12
    ’nın
    0.10
    'nın
    0.10
    eus
    0.10
    issance
    0.10
    ught
    0.10
    ugh
    0.09
    erts
    0.09
    frica
    0.09
    ughter
    0.09
    Activations Density 0.922%

    No Known Activations