© 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. 118302
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on"

    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
    èĪ
    -0.07
     mé
    -0.06
    éis
    -0.06
     vå
    -0.06
     cen
    -0.06
     Esc
    -0.06
    _ipc
    -0.06
     Jeho
    -0.06
    ascript
    -0.06
    abad
    -0.06
    POSITIVE LOGITS
    aim
    0.07
    aversable
    0.07
    ase
    0.07
    HLT
    0.06
    pie
    0.06
    lyph
    0.06
    eree
    0.06
     Nu
    0.06
     Grove
    0.06
    579
    0.06
    Activations Density 0.000%

    No Known Activations