© 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. 126090
    Prev
    Next
    INDEX
    Explanations

    Logging/printing

    np_max-act · gemini-2.0-flash

    This neuron fires on logging calls or log‐related tokens (e.g. console.log, println, NSLog, “logged,” etc.).

    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
    .Decode
    -0.06
    Leon
    -0.06
     shaft
    -0.06
    makes
    -0.06
    colon
    -0.06
    Maker
    -0.06
    ・マ
    -0.06
    attached
    -0.06
    ingers
    -0.06
    (metadata
    -0.06
    POSITIVE LOGITS
     contin
    0.07
    /sources
    0.06
     сопров
    0.06
    atasets
    0.06
     يق
    0.06
     Superv
    0.06
    航空
    0.06
     بلند
    0.06
     الذين
    0.06
     latest
    0.06
    Activations Density 0.028%

    No Known Activations