© 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. 7-RESID-POST-AA
    11. 78606
    Prev
    Next
    INDEX
    Explanations

    reasoning and justification

    np_max-act · gemini-2.0-flash

    words and short phrases that signal reasoning, cause, or discourse-connective (explanatory/contrasting) structure.

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scandal
    -0.06
    	signal
    -0.06
     driven
    -0.06
     Charger
    -0.06
     الميلاد
    -0.06
     Sergio
    -0.06
     جزء
    -0.06
    ским
    -0.06
    .Resolve
    -0.06
     princes
    -0.06
    POSITIVE LOGITS
    군요
    0.07
     花
    0.07
     ROS
    0.06
     речі
    0.06
     เท
    0.06
    đ
    0.06
    cljs
    0.06
    �
    0.06
     je
    0.06
    ξεις
    0.06
    Activations Density 0.125%

    No Known Activations