© 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. 73896
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting tokens that represent programmatic identifiers or codes (e.g., GUIDs, IDs, codes, names, addresses).

    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
    Pes
    -0.07
    .port
    -0.07
    Bat
    -0.07
    }.${
    -0.07
    ision
    -0.06
     Pon
    -0.06
    _wait
    -0.06
    ResultsController
    -0.06
    ibe
    -0.06
    .er
    -0.06
    POSITIVE LOGITS
    irror
    0.06
    (target
    0.06
    لمات
    0.06
     &&
    0.06
    =:
    0.06
     жит
    0.06
    nick
    0.06
     disposing
    0.06
    _"
    0.06
     sid
    0.06
    Activations Density 0.076%

    No Known Activations