© 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. 81246
    Prev
    Next
    INDEX
    Explanations

    names of political leaders and their titles

    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
    ivor
    -0.07
    eki
    -0.07
    ntl
    -0.07
     kå
    -0.07
    anja
    -0.07
    iode
    -0.07
    ámara
    -0.06
    oder
    -0.06
    er
    -0.06
    LOCKS
    -0.06
    POSITIVE LOGITS
    太éĥİ
    0.07
    /rem
    0.06
     Ser
    0.06
     Ale
    0.05
     Tay
    0.05
    ilter
    0.05
     Cristina
    0.05
    çŁ¢
    0.05
    (IB
    0.05
     Meg
    0.05
    Activations Density 0.004%

    No Known Activations