© 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. 55451
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to innovation and creativity

    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
    antor
    -0.09
    aban
    -0.08
    äm
    -0.07
     Zimmer
    -0.06
    ipple
    -0.06
    uja
    -0.06
    ucker
    -0.06
     Philosoph
    -0.06
    atty
    -0.06
    sume
    -0.06
    POSITIVE LOGITS
    IGHL
    0.07
    ARIO
    0.06
    ario
    0.06
     Lav
    0.06
    435
    0.06
    pons
    0.06
    737
    0.06
    odes
    0.06
     lav
    0.06
    352
    0.06
    Activations Density 0.000%

    No Known Activations