© 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. 110496
    Prev
    Next
    INDEX
    Explanations

    Foundation

    np_max-act · gemini-2.0-flash

    This neuron activates whenever it encounters the word “foundation,” in either capitalized or lower‐case form.

    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
    列
    -0.07
     RET
    -0.06
    誤
    -0.06
    Jim
    -0.06
    Edit
    -0.06
    Vol
    -0.06
    -part
    -0.06
    /met
    -0.06
     dynamic
    -0.06
     encrypt
    -0.06
    POSITIVE LOGITS
     Foundation
    0.17
     foundation
    0.14
    Foundation
    0.12
     foundations
    0.11
    foundation
    0.10
     COVER
    0.10
     Foundations
    0.09
    фф
    0.08
    础
    0.08
     NSF
    0.08
    Activations Density 0.009%

    No Known Activations