© 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. 58866
    Prev
    Next
    INDEX
    Explanations

    continue reading

    np_max-act · gemini-2.0-flash

    references to food and flavors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on “read on” or “keep reading” style calls-to-action that prompt the reader to continue.

    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
    .configuration
    -0.06
     pressures
    -0.06
    ocs
    -0.06
     Twenty
    -0.06
     referred
    -0.06
    ‪
    -0.05
     Graphic
    -0.05
    bitmap
    -0.05
     colony
    -0.05
     Thomas
    -0.05
    POSITIVE LOGITS
    人
    0.07
     Fiat
    0.07
    utral
    0.06
    OID
    0.06
    υκ
    0.06
    firefox
    0.06
     تز
    0.06
     MOUSE
    0.06
    وجه
    0.06
    RET
    0.06
    Activations Density 0.008%

    No Known Activations