© 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. 128076
    Prev
    Next
    INDEX
    Explanations

    verbs related to writing and creative production

    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
    æĤł
    -0.08
    éro
    -0.08
    DY
    -0.07
    vanished
    -0.07
     ëĮĢìĥģ
    -0.07
    043
    -0.07
    guild
    -0.07
    _COMPILE
    -0.07
    KHTML
    -0.07
    /loose
    -0.07
    POSITIVE LOGITS
     many
    0.09
     several
    0.08
     numerous
    0.08
     some
    0.07
     zahl
    0.07
     "
    0.06
     countless
    0.06
    inton
    0.06
     Numerous
    0.06
    许å¤ļ
    0.06
    Activations Density 0.020%

    No Known Activations