© 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. 74063
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting tokens that appear as items in explicit enumerations or lists (e.g. names in a recipient list or keywords in a code/SQL‐keyword array).

    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
    mart
    -0.07
     ماد
    -0.07
    claims
    -0.07
    ніч
    -0.06
    dyž
    -0.06
    wang
    -0.06
    uD
    -0.06
    พวก
    -0.06
    .annotations
    -0.06
    려요
    -0.06
    POSITIVE LOGITS
    	inline
    0.06
    .CR
    0.06
     recession
    0.06
     resident
    0.06
     relieve
    0.06
    _ASSOC
    0.06
     κυ
    0.06
    ик
    0.05
     ficken
    0.05
    _categoria
    0.05
    Activations Density 0.067%

    No Known Activations