© 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. 57068
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    code related to class definitions in object-oriented programming.

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

    This neuron responds to C++ source‐code tokens—especially header‐include and template syntax (e.g. “#include”, “<…>”, “::”, “.H”)—i.e. it flags C++ code constructs.

    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
    management
    -0.07
    _billing
    -0.07
     Güvenlik
    -0.07
     undermines
    -0.06
     restructuring
    -0.06
    (土
    -0.06
     decryption
    -0.06
    032
    -0.06
    ovně
    -0.06
    !("
    -0.06
    POSITIVE LOGITS
     lum
    0.06
    口
    0.06
    inia
    0.06
     thought
    0.06
    winner
    0.06
    _enabled
    0.06
    .align
    0.06
    slice
    0.06
    _elem
    0.06
    FE
    0.05
    Activations Density 0.007%

    No Known Activations