© 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. 38935
    Prev
    Next
    INDEX
    Explanations

    persist

    np_max-act · gemini-2.0-flash

    This neuron detects the character sequence “istant,” i.e. tokens containing the suffix “-istant.”

    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
    	df
    -0.07
    (IConfiguration
    -0.07
    -scal
    -0.06
    'na
    -0.06
    ufact
    -0.06
    rozen
    -0.06
    ocop
    -0.06
    ptest
    -0.06
    (Collectors
    -0.06
     feat
    -0.06
    POSITIVE LOGITS
     php
    0.07
     стоит
    0.07
     plagued
    0.07
     Vlad
    0.06
     persistent
    0.06
    dao
    0.06
     pressing
    0.06
     çalış
    0.06
     никто
    0.06
     survivors
    0.06
    Activations Density 0.038%

    No Known Activations