© 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. 37263
    Prev
    Next
    INDEX
    Explanations

    addr

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on identifier tokens that refer to addresses (i.e. the “addr” part of names like Sockaddr, RawSockaddr, function parameters named addr, etc.).

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

    license-related terms and copyright information.

    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
    .FAIL
    -0.07
    sequence
    -0.06
    Depending
    -0.06
     computers
    -0.06
    	font
    -0.06
    _properties
    -0.06
     $↵↵
    -0.06
    企業
    -0.06
    ("--------------------------------
    -0.06
    unci
    -0.06
    POSITIVE LOGITS
     inconvenient
    0.07
     reconc
    0.06
     Beaver
    0.06
     itch
    0.06
     sinking
    0.06
     üye
    0.06
    StackNavigator
    0.06
    abis
    0.06
     booming
    0.06
     Pessoa
    0.06
    Activations Density 0.000%

    No Known Activations