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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 110343
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    elements related to programming and system drivers.

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

    The neuron primarily activates on C/C++ preprocessor include directives (the “#include <…>” lines).

    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
    翼
    -0.07
    wife
    -0.07
     altru
    -0.07
    zych
    -0.07
     tostring
    -0.07
    _regeneration
    -0.06
    modo
    -0.06
    Pitch
    -0.06
    .friends
    -0.06
    zik
    -0.06
    POSITIVE LOGITS
     Including
    0.07
     milestones
    0.06
    ถาน
    0.06
     associative
    0.06
     facilitating
    0.06
    compet
    0.06
     scant
    0.06
     커
    0.06
     daha
    0.06
    SS
    0.06
    Activations Density 0.005%

    No Known Activations