© 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. 57869
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron activates on discussion of chemical reaction rates or “chemical activity” in gases, especially references to reactant concentrations or partial pressures.

    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
     pocket
    -0.06
    -0.06
    bcrypt
    -0.06
    による
    -0.06
     pants
    -0.06
    Bel
    -0.06
    Education
    -0.06
     background
    -0.06
    uitable
    -0.06
     bcrypt
    -0.06
    POSITIVE LOGITS
    _supp
    0.07
    °}
    0.07
    الد
    0.06
     digitally
    0.06
     điển
    0.06
    unwrap
    0.06
     pán
    0.06
     котор
    0.06
    ufreq
    0.06
    صة
    0.06
    Activations Density 0.045%

    No Known Activations