© 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. 127083
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash

    structured data formats and configuration settings in code.

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

    The neuron flags file‐path glob patterns (e.g. “**” and “/*.ts”) in configuration includes/excludes.

    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
    precation
    -0.07
    .qml
    -0.07
    ,
↵
↵
    -0.07
    ("~
    -0.07
     Goa
    -0.07
     newObj
    -0.06
    리아
    -0.06
    _editor
    -0.06
     stringByAppendingString
    -0.06
     Vale
    -0.06
    POSITIVE LOGITS
     LCS
    0.07
    ō
    0.06
    okol
    0.06
     той
    0.06
    nik
    0.06
    friend
    0.06
    评
    0.06
    寸
    0.06
     ли
    0.06
     Scientology
    0.06
    Activations Density 0.004%

    No Known Activations