© 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. 28179
    Prev
    Next
    INDEX
    Explanations

    names and personal identifiers related to individuals

    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
    ellen
    -0.09
    gı
    -0.08
    æķ·
    -0.08
    ĥn
    -0.08
    .scalablytyped
    -0.08
    ysa
    -0.08
    _________________↵↵
    -0.08
    ¦æĥħ
    -0.08
     saja
    -0.08
    اÛĮØ´
    -0.07
    POSITIVE LOGITS
    0.06
    0.06
     fit
    0.05
    âĢ¦↵
    0.05
     âĢ¦↵
    0.05
    ↵
    0.05
     supply
    0.05
    宾
    0.05
     Radi
    0.05
     add
    0.05
    Activations Density 0.001%

    No Known Activations