© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 43343
    Prev
    Next
    INDEX
    Explanations

    biological/medical studies

    np_max-act · gemini-2.0-flash

    The neuron fires on technical scientific process and method terms—especially gerundive or hyphenated action nouns like “analysis,” “signaling,” “activation,” and “-derived.”

    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
    書
    -0.07
     control
    -0.06
     ln
    -0.06
     delim
    -0.06
     pris
    -0.06
    etailed
    -0.06
    kla
    -0.06
    .DropDown
    -0.06
    _vect
    -0.06
    Static
    -0.06
    POSITIVE LOGITS
     withholding
    0.07
    tej
    0.07
    的声音
    0.06
     nghị
    0.06
     Aur
    0.06
     flowers
    0.06
     Lesb
    0.06
    edb
    0.06
     unexpectedly
    0.06
     Měst
    0.06
    Activations Density 0.140%

    No Known Activations