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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 50486
    Prev
    Next
    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash

    It detects leading‐whitespace tokens (indentation) in the C++ source, i.e. it lights up on the spaces at the start of indented lines.

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

    technical terms and definitions related to programming, particularly in a mathematical or computational context.

    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
     Madd
    -0.07
    อล
    -0.07
    ря
    -0.07
     reef
    -0.06
    adamente
    -0.06
    ив
    -0.06
     lev
    -0.06
     قب
    -0.06
     định
    -0.06
     modific
    -0.06
    POSITIVE LOGITS
    ="./
    0.06
    .Exit
    0.06
     exit
    0.06
    gewater
    0.06
    ิ์
    0.06
     spokesperson
    0.06
    เกม
    0.06
    stderr
    0.06
    _Run
    0.06
    utch
    0.06
    Activations Density 0.007%

    No Known Activations