© 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 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. 58745
    Prev
    Next
    INDEX
    Explanations

    references to education and its impact on communities

    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
    racial
    -0.07
     Tone
    -0.07
     Sphinx
    -0.06
     fac
    -0.06
     Fet
    -0.06
     racial
    -0.06
    çľ
    -0.06
    cooldown
    -0.05
    ahoma
    -0.05
    êµIJ
    -0.05
    POSITIVE LOGITS
     Satellite
    0.07
     Dropout
    0.07
     attendance
    0.07
     Attendance
    0.07
    itore
    0.07
     먼
    0.07
     Sender
    0.07
     dziewcz
    0.06
     dropout
    0.06
     absentee
    0.06
    Activations Density 0.026%

    No Known Activations