© 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. 9-LLAMASCOPE-RES-131K
    11. 97976
    Prev
    Next
    INDEX
    Explanations

    quotes or speech fragments related to political dialogue

    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
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.07
     karak
    -0.07
    огод
    -0.07
    ÑĪки
    -0.07
    ibold
    -0.07
    kol
    -0.07
    xee
    -0.06
     Kral
    -0.06
    posables
    -0.06
    asu
    -0.06
    POSITIVE LOGITS
    iten
    0.06
    nete
    0.06
    enden
    0.06
    Set
    0.06
     --------------------------------------------------------------------------------
    0.05
     set
    0.05
     Salv
    0.05
    usk
    0.05
     clo
    0.05
     Plat
    0.05
    Activations Density 0.006%

    No Known Activations