© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 572
    Prev
    Next
    INDEX
    Explanations

    calc

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially CSS numeric literals (e.g. plain numbers, decimals, percentages, and values inside calc()).

    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
    .binary
    -0.07
    FONT
    -0.07
    DIS
    -0.07
    Mate
    -0.07
    tyard
    -0.06
    SHORT
    -0.06
    isted
    -0.06
    ‌ترین
    -0.06
    _texts
    -0.06
    -issue
    -0.06
    POSITIVE LOGITS
     compassionate
    0.06
     Mein
    0.06
     hük
    0.06
    larında
    0.06
     přisp
    0.06
    annels
    0.06
    _minutes
    0.06
     creamy
    0.06
     ListViewItem
    0.06
    ει
    0.06
    Activations Density 0.001%

    No Known Activations