© 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. 41224
    Prev
    Next
    INDEX
    Explanations

    ine

    np_max-act · gemini-2.0-flash

    The neuron detects the word “crystalline,” i.e. mentions of crystalline solids.

    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
     \
    -0.08
     مدير
    -0.07
     Prosec
    -0.06
     گزارش
    -0.06
    Girls
    -0.06
     운영자
    -0.06
    _BLUE
    -0.06
     pistols
    -0.06
    utoff
    -0.06
     MET
    -0.06
    POSITIVE LOGITS
    ine
    0.10
    in
    0.09
    ін
    0.09
    chain
    0.08
    ин
    0.08
    bite
    0.08
    ren
    0.08
    šli
    0.08
    بي
    0.08
    ise
    0.08
    Activations Density 0.002%

    No Known Activations