© 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. 42841
    Prev
    Next
    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash

    This neuron activates on the substring “sub” when it appears as a prefix in words (e.g. sub-category, sub-species, sub-technologies).

    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
     Pearce
    -0.08
    Karen
    -0.07
    Await
    -0.07
    iên
    -0.07
     fait
    -0.07
    ög
    -0.07
    ิทธ
    -0.07
     Karen
    -0.07
    ủng
    -0.07
     Gordon
    -0.07
    POSITIVE LOGITS
     Sub
    0.14
    (sub
    0.14
     sub
    0.14
    sub
    0.13
    Sub
    0.13
    .Sub
    0.12
    	sub
    0.12
     SUB
    0.11
     subs
    0.11
    SUB
    0.11
    Activations Density 0.040%

    No Known Activations