© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 43900
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    mentions of legal/regulatory restrictions, warnings, or advice to check laws and compliance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     їх
    -0.06
     erw
    -0.06
     unidad
    -0.06
    hh
    -0.06
     ENABLE
    -0.06
     helpless
    -0.06
    领域
    -0.06
    izik
    -0.06
     olsun
    -0.06
     prag
    -0.06
    POSITIVE LOGITS
    localStorage
    0.08
    undefined
    0.07
     muscle
    0.06
     distort
    0.06
     Requirements
    0.06
     squeezed
    0.06
    enta
    0.06
     unlocked
    0.06
    PLACE
    0.06
    cohol
    0.06
    Activations Density 0.246%

    No Known Activations