© 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 EvalsExportsinterp-engineNEWAPI 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. 58164
    Prev
    Next
    INDEX
    Explanations

    candidate evaluation

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of a student‐grading context—particularly the word “student” (and possessive forms) in teaching‐assistant or grading instructions.

    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
    avid
    -0.06
    Deploy
    -0.06
     回
    -0.06
     ilet
    -0.06
    ραβ
    -0.06
    Α
    -0.06
    andin
    -0.06
    жно
    -0.06
     SIN
    -0.06
     llen
    -0.06
    POSITIVE LOGITS
     Hoàng
    0.08
     userInfo
    0.07
     Purdue
    0.07
     Fifty
    0.07
    avatars
    0.06
     pressed
    0.06
     Very
    0.06
    谋
    0.06
     Sheffield
    0.06
     декабря
    0.06
    Activations Density 0.019%

    No Known Activations