© 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 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. 38241
    Prev
    Next
    INDEX
    Explanations

    circuit board packaging

    np_max-act · gemini-2.0-flash

    This neuron activates on technical terms related to electronic packaging and interconnection structures (e.g. substrates, interposers, printed circuit boards, and associated materials/methods).

    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
    _request
    -0.07
     tiener
    -0.07
     perceptions
    -0.07
     Nicol
    -0.07
     ring
    -0.07
    _ARM
    -0.07
     Physiology
    -0.06
    Prefs
    -0.06
    -ring
    -0.06
     gg
    -0.06
    POSITIVE LOGITS
     гер
    0.07
    età
    0.06
    низ
    0.06
     угл
    0.06
    提升
    0.06
     самостоятельно
    0.06
     skilled
    0.06
     男
    0.06
    Fixed
    0.06
    ць
    0.05
    Activations Density 0.029%

    No Known Activations