Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129254
    Prev
    Next
    INDEX
    Explanations

    base number arithmetic

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the numeral‐system base when it appears in “In base X” statements.

    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
    .channel
    -0.07
    dra
    -0.06
     spider
    -0.06
     meditation
    -0.06
     SUBSTITUTE
    -0.06
    _words
    -0.06
    slaught
    -0.06
    рус
    -0.06
    .Hand
    -0.06
     latency
    -0.06
    POSITIVE LOGITS
     clums
    0.07
    (笑
    0.06
     erotique
    0.06
    �
    0.06
    organ
    0.06
     çalış
    0.06
     Základní
    0.06
     vý
    0.06
    تان
    0.06
     soğ
    0.06
    Activations Density 0.002%

    No Known Activations