© 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. 37872
    Prev
    Next
    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on capitalized named entities and titles (e.g. book or article names and proper nouns).

    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
    /XML
    -0.08
    디오
    -0.07
    開始
    -0.07
     pys
    -0.07
    ्पर
    -0.07
    λογή
    -0.06
    REF
    -0.06
    份
    -0.06
    primitive
    -0.06
     THEORY
    -0.06
    POSITIVE LOGITS
    'elle
    0.07
    >")↵
    0.06
     мер
    0.06
     discard
    0.06
    일
    0.06
     Homer
    0.06
    �
    0.06
    immutable
    0.06
     HOLDER
    0.06
     jose
    0.05
    Activations Density 0.053%

    No Known Activations