© 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. 73842
    Prev
    Next
    INDEX
    Explanations

    settle

    np_max-act · gemini-2.0-flash

    words related to historical events and places.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to past-tense or past-participle verb forms (e.g. words ending in “-ed”).

    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
    ítulo
    -0.07
     Bieber
    -0.07
     zákon
    -0.07
     Flesh
    -0.07
     translation
    -0.07
     Translation
    -0.06
    LOSE
    -0.06
    .oper
    -0.06
    	Camera
    -0.06
    enes
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.06
     Trek
    0.06
    _MAC
    0.06
    .Generic
    0.06
        ↵↵↵
    0.06
     gå
    0.06
     pParent
    0.06
     исключ
    0.06
    SENT
    0.06
     sqlalchemy
    0.06
    Activations Density 0.020%

    No Known Activations