© 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. 104606
    Prev
    Next
    INDEX
    Explanations

    questions related to ethical and societal implications

    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
    assing
    -0.07
    vä
    -0.06
     Sesso
    -0.06
    ï¸ı
    -0.06
    ih
    -0.06
    wh
    -0.06
    agon
    -0.06
    amp
    -0.06
    aut
    -0.06
     daher
    -0.06
    POSITIVE LOGITS
     Does
    0.07
     Pres
    0.07
     sup
    0.07
     does
    0.06
     елек
    0.06
     Is
    0.06
    acom
    0.06
    jian
    0.06
     NONE
    0.06
     Ø¢ÛĮا
    0.06
    Activations Density 0.025%

    No Known Activations