© 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. 98822
    Prev
    Next
    INDEX
    Explanations

    references to political roles and 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
    ongyang
    -0.08
     voks
    -0.08
    æľĭ
    -0.07
    дап
    -0.07
     åľ
    -0.07
    ikel
    -0.07
    âĢĮâĢĮ
    -0.07
    oun
    -0.07
    обÑĭ
    -0.07
     нал
    -0.06
    POSITIVE LOGITS
    zug
    0.07
    viewer
    0.06
     Hof
    0.06
    ValuePair
    0.05
    angered
    0.05
     on
    0.05
     Raven
    0.05
    toa
    0.05
    onation
    0.05
    aid
    0.05
    Activations Density 0.022%

    No Known Activations