© 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. 38173
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens in first‐person opinion or review statements (i.e. “I …,” “I loved …,” “I’m most proud …,” cast/crew reactions), marking subjective personal reactions.

    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
     fever
    -0.09
     cover
    -0.07
     stress
    -0.06
    48
    -0.06
    "c
    -0.06
    41
    -0.06
     Fever
    -0.06
    37
    -0.06
     staffing
    -0.06
     chip
    -0.06
    POSITIVE LOGITS
    lendirme
    0.07
     breathtaking
    0.07
     glowing
    0.07
     можете
    0.07
    Thêm
    0.07
    --[[
    0.06
     khuyến
    0.06
    زام
    0.06
    PRETTY
    0.06
    ，要
    0.06
    Activations Density 0.040%

    No Known Activations