© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57973
    Prev
    Next
    INDEX
    Explanations

    Redacted personal information

    np_max-act · gemini-2.0-flash

    This neuron activates on placeholder tokens representing named entities (e.g., "NAME_1," "NAME_2," etc.).

    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
     shaved
    -0.07
     опас
    -0.07
     neurotrans
    -0.06
    かない
    -0.06
     tokenizer
    -0.06
     Goldman
    -0.06
    \web
    -0.06
     murderers
    -0.06
     healthier
    -0.06
    .Xml
    -0.06
    POSITIVE LOGITS
     geg
    0.07
    iệc
    0.07
    Already
    0.06
    中文
    0.06
    ||(
    0.06
     Ez
    0.06
    Define
    0.06
     revival
    0.06
     Phần
    0.06
    数据
    0.06
    Activations Density 0.058%

    No Known Activations