© 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. 58037
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    The neuron is looking for comparative or degree-modifier words in style or tone instructions (e.g. “more,” “less,” “friendly,” “formal,” etc.).

    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
    ordes
    -0.06
     Somalia
    -0.06
    itis
    -0.06
    Shar
    -0.06
     abduction
    -0.06
    .Disabled
    -0.06
     pool
    -0.06
     Pool
    -0.06
     Shock
    -0.06
     pursue
    -0.06
    POSITIVE LOGITS
     tiene
    0.07
     Цент
    0.06
     Cannot
    0.06
     MÜ
    0.06
     enh
    0.06
    (NO
    0.06
     acab
    0.06
    머니
    0.06
    MT
    0.06
     klient
    0.06
    Activations Density 0.092%

    No Known Activations