© 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. 54378
    Prev
    Next
    INDEX
    Explanations

    07

    np_max-act · gemini-2.0-flash

    The neuron is specialized in detecting numeric identifier tokens (multi-digit numbers and hyphenated number sequences) typically found in file or page reference strings.

    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
    +z
    -0.07
    ‌اند
    -0.07
    orable
    -0.06
    ometimes
    -0.06
    .UnitTesting
    -0.06
     raided
    -0.06
     old
    -0.06
     attorneys
    -0.06
     intrusion
    -0.06
    .setAction
    -0.05
    POSITIVE LOGITS
    apellido
    0.07
     SignUp
    0.07
    BIND
    0.07
    (reference
    0.07
    ウォ
    0.06
     shy
    0.06
     architecture
    0.06
    -wrapper
    0.06
    -IS
    0.06
    流量
    0.06
    Activations Density 0.004%

    No Known Activations