© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89594
    Prev
    Next
    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash

    The neuron fires on square‐bracketed placeholders in command‐line usage strings (e.g. “[OPTIONS]”, “[arg]”).

    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
    urers
    -0.07
    .Not
    -0.07
    启
    -0.07
    оля
    -0.06
    graphs
    -0.06
     turquoise
    -0.06
     descendants
    -0.06
    ■
    -0.06
    	assertEquals
    -0.06
     несколько
    -0.06
    POSITIVE LOGITS
    Jul
    0.07
    (route
    0.07
    .lua
    0.06
     uğra
    0.06
     зай
    0.06
    .Dimension
    0.06
     aseg
    0.06
    swift
    0.06
    (tp
    0.06
    }".
    0.06
    Activations Density 0.013%

    No Known Activations