© 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
    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. 88943
    Prev
    Next
    INDEX
    Explanations

    research studies with numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens (counts, measurements, percentages, and statistical values).

    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
    械
    -0.07
    _tgt
    -0.07
     француз
    -0.07
     речі
    -0.07
     solar
    -0.06
     russ
    -0.06
    弱
    -0.06
     로
    -0.06
    EOS
    -0.06
     defaults
    -0.06
    POSITIVE LOGITS
     nouvel
    0.06
     encuent
    0.06
    Newsletter
    0.05
    .JOptionPane
    0.05
    \Order
    0.05
    acom
    0.05
    .Month
    0.05
    adoo
    0.05
     Weather
    0.05
    อกจากน
    0.05
    Activations Density 0.013%

    No Known Activations