© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90947
    Prev
    Next
    INDEX
    Explanations

    Blog posts

    np_max-act · gemini-2.0-flash

    This neuron fires most strongly on brand, product, and other proper-name tokens.

    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
    346
    -0.08
     پروژه
    -0.07
    43
    -0.06
     امن
    -0.06
     periodically
    -0.06
     entertainment
    -0.06
    GBP
    -0.06
     appliances
    -0.06
     黄
    -0.06
     αυτά
    -0.06
    POSITIVE LOGITS
    /media
    0.06
    eral
    0.06
    .Interop
    0.06
    ITTE
    0.06
    icers
    0.06
    deposit
    0.06
    บาล
    0.06
     арми
    0.06
    _EXPR
    0.06
    iez
    0.06
    Activations Density 0.135%

    No Known Activations