© 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. 86634
    Prev
    Next
    INDEX
    Explanations

    mentions of government officials 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
    alam
    -0.07
    izedName
    -0.07
    noch
    -0.07
    otte
    -0.06
    thest
    -0.06
    curring
    -0.06
    elage
    -0.06
    AMERA
    -0.06
    inks
    -0.06
    -cols
    -0.06
    POSITIVE LOGITS
     deleg
    0.07
     Schul
    0.07
    erli
    0.07
     delegation
    0.06
    ague
    0.06
     благ
    0.06
    _CSS
    0.06
    주ìĭľ
    0.06
    orb
    0.06
    éĦ
    0.06
    Activations Density 0.011%

    No Known Activations