© 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. 36983
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    The neuron activates on named entities—proper nouns like product or company names, technology/model names, place names, or other specific names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    differences between cities in terms of cultural significance.

    oai_token-act-pair · gpt-4o-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
    -fit
    -0.07
     roku
    -0.07
     Positive
    -0.07
     informative
    -0.07
     hen
    -0.07
     valuable
    -0.06
    輕
    -0.06
    eros
    -0.06
     заболева
    -0.06
    _if
    -0.06
    POSITIVE LOGITS
    	fn
    0.06
    _Version
    0.06
     './../../
    0.06
     './../
    0.06
    	Double
    0.06
    <translation
    0.06
    Export
    0.06
     Farr
    0.06
    vere
    0.06
    ATYPE
    0.06
    Activations Density 0.072%

    No Known Activations