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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16181
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash

    The neuron detects decimal numeric literals (i.e. floating‐point 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
     understandably
    -0.07
    processors
    -0.07
    ึกษา
    -0.06
     �
    -0.06
     ATTR
    -0.06
     đại
    -0.06
    аци
    -0.06
    دانلود
    -0.06
     صند
    -0.06
     teens
    -0.06
    POSITIVE LOGITS
    agedList
    0.06
     Ping
    0.06
    +h
    0.06
    riminal
    0.06
     amour
    0.06
    pecia
    0.06
     monthly
    0.06
     reopened
    0.06
     agricultural
    0.06
     Wet
    0.06
    Activations Density 0.013%

    No Known Activations