© 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. 74293
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational initiatives and support for underrepresented students

    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
    nda
    -0.07
    ully
    -0.06
    å±ŀ
    -0.06
    Ñĸно
    -0.06
    rek
    -0.06
    rys
    -0.06
     à¸Ĺาà¸ĩ
    -0.06
    çľģ
    -0.06
    ems
    -0.06
    rok
    -0.06
    POSITIVE LOGITS
    .FontStyle
    0.07
    emailer
    0.06
    orget
    0.06
    érc
    0.06
    immel
    0.06
    andas
    0.06
     Mobil
    0.06
    ocz
    0.06
    ائ
    0.06
     Pascal
    0.06
    Activations Density 0.004%

    No Known Activations