© 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. 6183
    Prev
    Next
    INDEX
    Explanations

    wrong, mistake

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens in questions that ask “what’s wrong with …,” i.e. it detects when the user is asking what’s wrong with some code or input.

    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
     Randolph
    -0.07
    ungeon
    -0.07
     Poland
    -0.06
    nesc
    -0.06
    Rand
    -0.06
     ده
    -0.06
     >/
    -0.06
     Regression
    -0.06
     Decision
    -0.06
     storefront
    -0.06
    POSITIVE LOGITS
     Oct
    0.08
     Feb
    0.07
     bottom
    0.07
    ”。
    0.06
    Ư�
    0.06
    jj
    0.06
    (sf
    0.06
     Sep
    0.06
     Nov
    0.06
    �能
    0.06
    Activations Density 0.025%

    No Known Activations