© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123541
    Prev
    Next
    INDEX
    Explanations

    references to early education and related age groups

    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
    CTX
    -0.07
    ãģĭãģĹ
    -0.07
    okia
    -0.07
    anj
    -0.07
    авиÑģ
    -0.06
     Sty
    -0.06
    ë¥
    -0.06
    ippo
    -0.06
     Cumhuriyet
    -0.06
    ãĤ·ãĥ£ãĥ«
    -0.06
    POSITIVE LOGITS
     Attendance
    0.08
    quito
    0.07
    ediator
    0.07
    .gov
    0.07
     attendance
    0.06
    .setTo
    0.06
    gov
    0.06
    abay
    0.06
    ulty
    0.06
    orthand
    0.06
    Activations Density 0.012%

    No Known Activations