© 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. 129993
    Prev
    Next
    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash

    The neuron fires on the character‐sequence fragments of “Kermanshah,” i.e. it’s detecting mentions of that Iranian province name in place descriptions.

    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
     Atlanta
    -0.07
     Savannah
    -0.07
     Asp
    -0.07
     сор
    -0.06
     mensen
    -0.06
    AVING
    -0.06
     peripherals
    -0.06
     Georgia
    -0.06
    ђ
    -0.06
     workout
    -0.06
    POSITIVE LOGITS
    完整
    0.07
    �
    0.07
    eso
    0.06
     nüfus
    0.06
     svn
    0.06
    arih
    0.06
    dığı
    0.06
    Parsed
    0.06
    út
    0.06
     xã
    0.06
    Activations Density 0.243%

    No Known Activations