© 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. 14602
    Prev
    Next
    INDEX
    Explanations

    references to specific historical figures 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
    iny
    -0.07
    aub
    -0.07
    enty
    -0.07
    ·¨
    -0.07
    INY
    -0.07
    ivet
    -0.07
     поÑħ
    -0.06
    Æ¡i
    -0.06
    issent
    -0.06
    èn
    -0.06
    POSITIVE LOGITS
     office
    0.09
    pery
    0.08
     position
    0.08
     holder
    0.07
    office
    0.07
     Fem
    0.07
     duties
    0.06
     role
    0.06
     sal
    0.06
     job
    0.06
    Activations Density 0.015%

    No Known Activations