© 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. 54758
    Prev
    Next
    INDEX
    Explanations

    language related to social gatherings and family connections

    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
     Pu
    -0.06
     CommandType
    -0.06
     Sez
    -0.06
    æ¡Ĥ
    -0.06
    леÑĤ
    -0.06
    portlet
    -0.06
     exciting
    -0.06
    Orth
    -0.05
    ä¹IJ
    -0.05
     gib
    -0.05
    POSITIVE LOGITS
     funeral
    0.10
     Funeral
    0.09
     attendance
    0.09
     coffin
    0.08
     mourn
    0.07
     closure
    0.07
    è¡
    0.07
     Attendance
    0.07
     incons
    0.07
     bere
    0.07
    Activations Density 0.009%

    No Known Activations