© 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 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. 45021
    Prev
    Next
    INDEX
    Explanations

    Adverbs

    np_max-act · gemini-2.0-flash

    This neuron detects degree-or frequency-qualifying words or phrases (e.g. “most,” “commonly,” “officially,” “ever-increasing”) that modify how strongly or how often something is done.

    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
     futile
    -0.07
     intercept
    -0.07
    щее
    -0.07
    REAK
    -0.07
    +_
    -0.07
    VARCHAR
    -0.06
    890
    -0.06
     klu
    -0.06
    Creature
    -0.06
     Fe
    -0.06
    POSITIVE LOGITS
    	continue
    0.07
    @testable
    0.07
    <body
    0.06
     Uns
    0.06
     NGOs
    0.06
     Ramirez
    0.06
     uns
    0.06
    	finally
    0.06
     negocio
    0.06
    .News
    0.06
    Activations Density 0.072%

    No Known Activations