© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58793
    Prev
    Next
    INDEX
    Explanations

    iron

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the chemical element iron (including “iron,” its symbol “Fe,” and related compounds).

    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
     створення
    -0.07
     BU
    -0.07
    ribly
    -0.07
    ース
    -0.07
    .contentType
    -0.07
    chk
    -0.07
    ческим
    -0.06
    GetString
    -0.06
     BEST
    -0.06
    扣
    -0.06
    POSITIVE LOGITS
     iron
    0.11
     Iron
    0.11
    Iron
    0.08
     getValue
    0.07
     Fe
    0.07
     желез
    0.07
     للس
    0.07
    (items
    0.07
     Ferr
    0.06
    】↵↵
    0.06
    Activations Density 0.009%

    No Known Activations