© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42958
    Prev
    Next
    INDEX
    Explanations

    random snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on proper‐name tokens (e.g. person names or month names) in formal legal text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     content
    -0.07
     gallery
    -0.07
    元
    -0.06
    jump
    -0.06
     leader
    -0.06
     "[
    -0.06
     všech
    -0.06
     partir
    -0.06
    -Bar
    -0.06
     cryptocurrency
    -0.06
    POSITIVE LOGITS
    _OPENGL
    0.06
    .Course
    0.06
    	className
    0.06
    ่งชาต
    0.06
     coarse
    0.06
     vertical
    0.06
    .customer
    0.06
     ensued
    0.06
     classy
    0.06
     concurrently
    0.06
    Activations Density 0.024%

    No Known Activations