© 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
    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. 9336
    Prev
    Next
    INDEX
    Explanations

    possibility/capability

    np_max-act · gemini-2.0-flash

    This neuron responds to emphatic conclusion phrases expressing absolute negation or finality, e.g. “nothing could ever tear them apart.”

    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
    Fold
    -0.07
     inconsistencies
    -0.07
     theories
    -0.07
     notifications
    -0.07
    کش
    -0.06
     theorists
    -0.06
     HIT
    -0.06
    ération
    -0.06
     Documentation
    -0.06
    rå
    -0.06
    POSITIVE LOGITS
    antee
    0.06
     ginger
    0.06
     оптим
    0.06
     bonding
    0.06
    hythm
    0.06
    ！↵
    0.06
     ファ
    0.06
     caval
    0.06
    '><
    0.05
     Dhabi
    0.05
    Activations Density 0.010%

    No Known Activations