© 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
    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. 733
    Prev
    Next
    INDEX
    Explanations

    Extr

    np_max-act · gemini-2.0-flash

    The neuron fires on any occurrence of the “dextr-” prefix (as in dextran, dextranase, dextrous, etc.).

    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
     Off
    -0.07
     Willie
    -0.06
     readings
    -0.06
     oid
    -0.06
     ROUT
    -0.06
    عنی
    -0.06
     vind
    -0.06
     (?)
    -0.06
    Pie
    -0.06
     siege
    -0.06
    POSITIVE LOGITS
     Dexter
    0.09
    extr
    0.08
    ers
    0.07
    er
    0.07
     Baxter
    0.07
    EX
    0.07
    ER
    0.07
    avin
    0.07
     дев
    0.07
    novation
    0.07
    Activations Density 0.001%

    No Known Activations