© 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. 91533
    Prev
    Next
    INDEX
    Explanations

    video games

    np_max-act · gemini-2.0-flash

    The neuron specializes in picking out video‐game titles and sequel/version indicators (e.g. names followed or interspersed with numerals or Roman numerals).

    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
    需
    -0.06
     Beckham
    -0.06
    そんな
    -0.06
     EQ
    -0.06
     плот
    -0.06
    Account
    -0.06
    ason
    -0.06
    _TREE
    -0.06
     όλα
    -0.06
     invoice
    -0.06
    POSITIVE LOGITS
    indent
    0.07
     intimidate
    0.06
     sö
    0.06
     avons
    0.06
     Florian
    0.06
     Rotterdam
    0.06
     april
    0.06
    VL
    0.06
     rallies
    0.06
    !(
    0.06
    Activations Density 0.049%

    No Known Activations