© 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. 54265
    Prev
    Next
    INDEX
    Explanations

    crystall

    np_max-act · gemini-2.0-flash

    The neuron activates on technical terms describing polymer microstructure—especially words related to crystallization, phase‐separation, microdomains, and elastic/thermoplastic segment morphology.

    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
    Vision
    -0.06
    stddef
    -0.06
    blue
    -0.06
    JSImport
    -0.06
     출장
    -0.06
     Quiz
    -0.06
     デ
    -0.06
    .dgv
    -0.06
    .WEST
    -0.06
    .marker
    -0.06
    POSITIVE LOGITS
    ...,
    0.07
     ''.
    0.06
    {i
    0.06
    ropdown
    0.06
     Пот
    0.06
     tester
    0.06
    leck
    0.06
    952
    0.06
     andre
    0.06
     clinically
    0.06
    Activations Density 0.005%

    No Known Activations