© 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. 44264
    Prev
    Next
    INDEX
    Explanations

    code-related text

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens from software license or copyright headers, especially uppercase or title-case terms like “Copyright,” “GPL,” “Public,” and related license boilerplate.

    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
     روشن
    -0.07
    ViewPager
    -0.07
     Cure
    -0.07
    Fun
    -0.06
     дом
    -0.06
     Rif
    -0.06
    MF
    -0.06
    PHA
    -0.06
    _timestamp
    -0.06
     NOM
    -0.06
    POSITIVE LOGITS
     @"↵
    0.07
    сли
    0.07
    .fetchone
    0.07
    -worker
    0.06
    mouse
    0.06
     shift
    0.06
     CAPITAL
    0.06
    -proxy
    0.06
     Advisory
    0.06
    .SQLException
    0.06
    Activations Density 0.045%

    No Known Activations