© 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. 108939
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron appears to be essentially inactive (a “dead” neuron) and does not reliably detect any particular token pattern.

    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
    .include
    -0.07
     biç
    -0.06
     Www
    -0.06
     Level
    -0.06
    (stage
    -0.06
    917
    -0.06
     ff
    -0.06
     polluted
    -0.06
     ona
    -0.06
     fetal
    -0.06
    POSITIVE LOGITS
    τερ
    0.06
     الام
    0.06
    bourne
    0.06
     Bliss
    0.06
    oslav
    0.06
    的一
    0.06
    jed
    0.05
     restroom
    0.05
     PLC
    0.05
    roit
    0.05
    Activations Density 0.009%

    No Known Activations