© 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. 7361
    Prev
    Next
    INDEX
    Explanations

    code manipulation

    np_max-act · gemini-2.0-flash

    This neuron lights up on identifiers that look like function or method names in source code.

    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
    ��
    -0.06
     paylaş
    -0.06
    .u
    -0.06
    EditMode
    -0.06
    „ظ
    -0.06
    Mad
    -0.06
    Ben
    -0.06
    cie
    -0.06
    سين
    -0.06
    街
    -0.06
    POSITIVE LOGITS
    €↵
    0.08
    UIApplication
    0.08
     fread
    0.07
    に見
    0.06
    payments
    0.06
     bothers
    0.06
    ?><?
    0.06
     roleId
    0.06
    PostExecute
    0.06
    -dist
    0.06
    Activations Density 0.021%

    No Known Activations