© 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. 38145
    Prev
    Next
    INDEX
    Explanations

    _once

    np_max-act · gemini-2.0-flash

    code related to PHP application structure and functionality.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags PHP import/include statements (e.g. require_once or include calls).

    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
     giai
    -0.07
    _Db
    -0.07
     zoals
    -0.07
    ()<
    -0.06
     healing
    -0.06
     布
    -0.06
    dish
    -0.06
     agrees
    -0.06
     милли
    -0.06
     glory
    -0.06
    POSITIVE LOGITS
    _once
    0.09
     přece
    0.07
     nonce
    0.06
     Challenger
    0.06
    ElapsedTime
    0.06
    quete
    0.06
    /history
    0.06
    .Concurrent
    0.06
     deactivated
    0.06
    。不过
    0.06
    Activations Density 0.000%

    No Known Activations