© 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. 130081
    Prev
    Next
    INDEX
    Explanations

    software/tech products

    np_max-act · gemini-2.0-flash

    The neuron activates on the names of enterprise integration/middleware software tools.

    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
    PropertyValue
    -0.07
     Say
    -0.06
     effects
    -0.06
     CUT
    -0.06
    Graphics
    -0.06
    Visibility
    -0.06
    .pl
    -0.06
     successors
    -0.06
    Ford
    -0.06
     количество
    -0.06
    POSITIVE LOGITS
     pás
    0.06
    чий
    0.06
    ignment
    0.06
    只是
    0.06
    çesi
    0.06
     breaker
    0.06
    _VOID
    0.06
    =C
    0.06
     bureaucrats
    0.05
    ])↵↵↵
    0.05
    Activations Density 0.157%

    No Known Activations