© 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. 44610
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on words that name or introduce organized actions, initiatives, or programs (e.g. “trial,” “campaign,” “export,” “full-court press”).

    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
     fitted
    -0.07
     extract
    -0.06
     }}
    -0.06
    ίγ
    -0.06
     McCorm
    -0.06
    _residual
    -0.06
    ostí
    -0.06
     كور
    -0.06
    edii
    -0.06
    FormGroup
    -0.06
    POSITIVE LOGITS
     آغاز
    0.08
     quay
    0.07
     rozp
    0.07
     interruption
    0.07
     Speedway
    0.07
     Seattle
    0.07
    ・・・
    0.07
    次
    0.06
     شروع
    0.06
     sett
    0.06
    Activations Density 0.031%

    No Known Activations