© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6960
    Prev
    Next
    INDEX
    Explanations

    curve

    np_max-act · gemini-2.0-flash

    The neuron detects decimal‐formatted numeric values (e.g. p-values, AUCs, ROC statistics) 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
    iangle
    -0.06
     PROGRAM
    -0.06
     Maver
    -0.06
    学院
    -0.06
    TPL
    -0.06
     Rover
    -0.06
    TOTAL
    -0.06
     Elasticsearch
    -0.06
     Mö
    -0.06
    $/
    -0.06
    POSITIVE LOGITS
    ifter
    0.07
    υν
    0.07
     mpfr
    0.07
    。（
    0.07
    нуть
    0.06
    inet
    0.06
    بالإنجليزية
    0.06
    debug
    0.06
     updateTime
    0.06
    irl
    0.06
    Activations Density 0.007%

    No Known Activations