© 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. 102637
    Prev
    Next
    INDEX
    Explanations

    true

    np_max-act · gemini-2.0-flash

    This neuron fires on additive transition adverbs (e.g. “also”) that signal inclusion of additional information.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phrases related to legislative processes and law.

    oai_token-act-pair · gpt-4o-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
    -zone
    -0.07
    _OCC
    -0.07
    食品
    -0.07
    CACHE
    -0.07
    Agents
    -0.07
     cycles
    -0.07
    园
    -0.07
    043
    -0.06
    -intensive
    -0.06
    الی
    -0.06
    POSITIVE LOGITS
     assertFalse
    0.06
     RHS
    0.06
     polls
    0.06
     Psy
    0.06
     sélection
    0.06
     additionally
    0.06
    _PREFIX
    0.06
     heap
    0.06
     Redistributions
    0.06
     comply
    0.06
    Activations Density 0.000%

    No Known Activations