© 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
    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. 91332
    Prev
    Next
    INDEX
    Explanations

    update

    np_max-act · gemini-2.0-flash

    The neuron detects metadata markers—especially “UPDATE” tags, timestamps, and similar update/time‐stamp notations in news text.

    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
     Colts
    -0.07
     rotterdam
    -0.07
    iphers
    -0.06
     enhancement
    -0.06
    	end
    -0.06
    ิงห
    -0.06
     liebe
    -0.06
    uki
    -0.06
     Estonia
    -0.06
    <A
    -0.06
    POSITIVE LOGITS
    んでいる
    0.07
    带
    0.07
     взгляд
    0.06
     INCIDENT
    0.06
    .getInput
    0.06
     время
    0.06
    Talking
    0.06
     TIMESTAMP
    0.06
    assertFalse
    0.06
    findFirst
    0.06
    Activations Density 0.019%

    No Known Activations