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

    Neuronpedia

    Jacobian LensNEW
    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. 57020
    Prev
    Next
    INDEX
    Explanations

    .hpp

    np_max-act · gemini-2.0-flash

    The neuron fires on Boost.MPL metafunction includes and MPL operator/type names (e.g. “and,” “bool,” “equal_to,” “if,” “or,” “plus,” “times,” 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
     tbody
    -0.06
     �
    -0.06
    $wp
    -0.06
     APP
    -0.06
    घ
    -0.06
    (CancellationToken
    -0.06
     댓글
    -0.06
     �
    -0.06
    .tmp
    -0.06
    .AutoSizeMode
    -0.06
    POSITIVE LOGITS
     amazingly
    0.07
    resource
    0.06
     itertools
    0.06
     Bollywood
    0.06
     ){↵↵
    0.06
     Animation
    0.06
     mismatch
    0.06
     пров
    0.06
    unlock
    0.06
     accountant
    0.06
    Activations Density 0.002%

    No Known Activations