© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13872
    Prev
    Next
    INDEX
    Explanations

    _CHECK or _ARG

    np_max-act · gemini-2.0-flash

    The neuron fires on Autoconf build‐system macro names and invocation tokens (e.g. uppercase AC_* directives like AC_CHECK_LIB, AC_ARG_ENABLE, AC_MSG_CHECKING, 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
     mirac
    -0.07
    paths
    -0.07
    .mdl
    -0.06
     largely
    -0.06
    К
    -0.06
    login
    -0.06
    �
    -0.06
     failing
    -0.06
     balances
    -0.06
    ク
    -0.06
    POSITIVE LOGITS
    _BYTES
    0.07
     mực
    0.07
    ->{'
    0.07
    (getResources
    0.07
    [file
    0.07
     molecules
    0.06
     adapter
    0.06
    RAW
    0.06
    ${
    0.06
    239
    0.06
    Activations Density 0.001%

    No Known Activations