© 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. 58583
    Prev
    Next
    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash

    The neuron fires on colloquial, subjective praise constructions—especially “’s so ADJ” patterns expressing strong positive evaluation.

    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
     whites
    -0.07
     dominates
    -0.06
    riangle
    -0.06
    อว
    -0.06
    öl
    -0.06
    Exercise
    -0.06
     uv
    -0.06
     solves
    -0.06
    national
    -0.06
    いた
    -0.06
    POSITIVE LOGITS
     handleChange
    0.08
    --------↵
    0.06
    STRU
    0.06
     없이
    0.06
    .findOne
    0.06
     �
    0.06
    .createStatement
    0.06
     �
    0.06
     نه
    0.06
     handleSubmit
    0.06
    Activations Density 0.035%

    No Known Activations