© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58316
    Prev
    Next
    INDEX
    Explanations

    words related to educational programs and community engagement

    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
    avig
    -0.07
    utsch
    -0.06
    ungi
    -0.06
    phere
    -0.06
    amburger
    -0.06
     scient
    -0.06
     Ø£Ùħ
    -0.06
     sey
    -0.06
     Scient
    -0.06
    aket
    -0.06
    POSITIVE LOGITS
     schools
    0.12
    schools
    0.11
     Schools
    0.10
     elementary
    0.09
     school
    0.07
    chool
    0.07
     Elementary
    0.07
     prisons
    0.07
    -school
    0.07
     Vis
    0.07
    Activations Density 0.048%

    No Known Activations