© 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. 744
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    This neuron activates on past‐tense or past-participle verb forms—i.e. words ending in “-ed.”

    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
     steam
    -0.08
    _put
    -0.07
     AOL
    -0.06
    -foot
    -0.06
    目的
    -0.06
     breeding
    -0.06
    ски
    -0.06
    ote
    -0.06
     пош
    -0.06
     використ
    -0.06
    POSITIVE LOGITS
    .Span
    0.07
     anarchists
    0.06
    _LA
    0.06
    ritable
    0.06
    .newInstance
    0.06
    тон
    0.06
     mús
    0.06
     polarity
    0.06
     notifies
    0.06
    HomeAs
    0.06
    Activations Density 0.285%

    No Known Activations