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. 80694
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects Java print‐out code, in particular System.out.println calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets that involve working with data structures and processing logic.

    oai_token-act-pair · gpt-4o-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
     notice
    -0.06
    .factor
    -0.06
     Borders
    -0.06
    (rr
    -0.06
    جا
    -0.06
    _CLR
    -0.06
     noteworthy
    -0.06
    NSE
    -0.06
     CFO
    -0.06
     evolutionary
    -0.06
    POSITIVE LOGITS
     getContext
    0.07
    .Con
    0.06
    efs
    0.06
    .poi
    0.06
    فة
    0.06
    fell
    0.06
    Concept
    0.06
     feature
    0.06
    _Channel
    0.06
     **
    0.06
    Activations Density 0.124%

    No Known Activations