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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91512
    Prev
    Next
    INDEX
    Explanations

    otive

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming industry sectors (e.g. aerospace, automotive, energy) indicating it’s looking for mentions of specific industries.

    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
     machine
    -0.07
     HAND
    -0.06
     neighbour
    -0.06
     sugar
    -0.06
     Mush
    -0.06
     poles
    -0.06
     DRM
    -0.06
     Kul
    -0.06
     Pole
    -0.06
     mereka
    -0.06
    POSITIVE LOGITS
     automotive
    0.12
     Automotive
    0.11
    TV
    0.07
     　 　
    0.07
    ımıza
    0.07
    .productId
    0.07
    vrolet
    0.07
     Aviation
    0.07
    атор
    0.07
    vc
    0.07
    Activations Density 0.010%

    No Known Activations