© 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. 44646
    Prev
    Next
    INDEX
    Explanations

    Industrial applications and chemicals

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of chemical‐industry product categories or materials (e.g. plastics, dyes, pharmaceuticals, adhesives).

    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
    ours
    -0.07
    ête
    -0.07
    OND
    -0.06
    aval
    -0.06
    sets
    -0.06
    anol
    -0.06
    Plot
    -0.06
     Zi
    -0.06
    aba
    -0.06
    (E
    -0.06
    POSITIVE LOGITS
    _WINDOWS
    0.07
     Blur
    0.07
     πρώ
    0.07
     architectures
    0.07
     kindergarten
    0.07
     originals
    0.06
    yıl
    0.06
     Vladimir
    0.06
    Modification
    0.06
    一个人
    0.06
    Activations Density 0.032%

    No Known Activations