© 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. 129372
    Prev
    Next
    INDEX
    Explanations

    words related to people or types of individuals

    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
     å©
    -0.06
    /books
    -0.06
    elage
    -0.06
     hormones
    -0.06
    apl
    -0.06
    اÙĬات
    -0.06
     glasses
    -0.06
    ypad
    -0.05
    rium
    -0.05
    voke
    -0.05
    POSITIVE LOGITS
    ENCE
    0.07
    endra
    0.07
    ization
    0.07
    erman
    0.07
    pedia
    0.07
    Evt
    0.07
    串
    0.06
    -related
    0.06
     Gors
    0.06
    ç¿
    0.06
    Activations Density 0.000%

    No Known Activations