© 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 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. 56643
    Prev
    Next
    INDEX
    Explanations

    procedures or actions

    np_max-act · gemini-2.0-flash

    The neuron fires on past-tense or past-participial verbs that describe procedural actions (e.g., “done,” “performed”).

    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
    协议
    -0.07
    dıktan
    -0.07
     Buna
    -0.07
    \Module
    -0.06
     Onun
    -0.06
    Industry
    -0.06
    рем
    -0.06
    วย
    -0.06
    ORY
    -0.06
     mission
    -0.06
    POSITIVE LOGITS
     '''
    0.08
    bugs
    0.07
    BAB
    0.07
     루
    0.07
    (predicate
    0.06
     affiliate
    0.06
    Redirect
    0.06
    apest
    0.06
     Mood
    0.06
     Ripple
    0.06
    Activations Density 0.118%

    No Known Activations