© 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. 13421
    Prev
    Next
    INDEX
    Explanations

    code/identifiers

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens (digits), especially numbers attached to identifiers.

    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
     NOW
    -0.07
     Euras
    -0.07
    /es
    -0.06
    _ca
    -0.06
    _delegate
    -0.06
    _AA
    -0.06
    ές
    -0.06
     LPC
    -0.06
    director
    -0.06
    θο
    -0.06
    POSITIVE LOGITS
    دة
    0.06
    осуд
    0.06
     stock
    0.06
    تح
    0.06
    me
    0.06
    Visibility
    0.06
    了一
    0.06
    テ
    0.06
     leans
    0.06
    یدی
    0.06
    Activations Density 0.035%

    No Known Activations