© 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. 59943
    Prev
    Next
    INDEX
    Explanations

    document or file links and references in web formats

    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
    adolu
    -0.08
    ÑĪкÑĥ
    -0.08
    relude
    -0.08
    qli
    -0.08
    алÑİ
    -0.07
    важа
    -0.07
    erk
    -0.07
    imore
    -0.07
     дело
    -0.07
    rys
    -0.07
    POSITIVE LOGITS
     amongst
    0.08
     among
    0.07
     B
    0.07
    ussen
    0.06
    ailer
    0.06
     Bet
    0.06
     "
    0.06
    ottes
    0.06
    attach
    0.06
     apart
    0.05
    Activations Density 0.013%

    No Known Activations