© 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. 30141
    Prev
    Next
    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash

    The neuron reliably fires on floating‐point numeric tokens (decimal numbers) in the text.

    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
    (NAME
    -0.07
    Zero
    -0.06
    .PER
    -0.06
    .Do
    -0.06
     від
    -0.06
    ，您
    -0.06
    (K
    -0.06
    irmed
    -0.06
    grey
    -0.06
    -feature
    -0.06
    POSITIVE LOGITS
     feas
    0.07
    ucht
    0.07
     cost
    0.07
    .nio
    0.07
     errorCode
    0.07
     quo
    0.07
     недел
    0.07
    linik
    0.07
     çıkart
    0.06
    UpdateTime
    0.06
    Activations Density 0.002%

    No Known Activations