© 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
    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. 5957
    Prev
    Next
    INDEX
    Explanations

    inert atmospheres/gases

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of inert‐gas or controlled‐atmosphere conditions (e.g. argon, nitrogen, N₂ atmosphere) in chemical processing steps.

    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
    isé
    -0.06
    ex
    -0.06
     healed
    -0.06
    리아
    -0.06
    饮
    -0.06
    _FIELDS
    -0.06
     điểm
    -0.06
     wsz
    -0.06
    quina
    -0.06
     needles
    -0.06
    POSITIVE LOGITS
    makes
    0.06
    _VERSION
    0.06
     MORE
    0.06
    (wp
    0.06
    sequelize
    0.06
    .Sql
    0.06
     QT
    0.06
     wrap
    0.06
     Burst
    0.06
     Technician
    0.06
    Activations Density 0.007%

    No Known Activations