© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92094
    Prev
    Next
    INDEX
    Explanations

    matrix

    np_max-act · gemini-2.0-flash

    This neuron detects code references to 4×4 transformation matrix operations (e.g. methods and properties like DirtyMatrix, Chain, SetScale, UpdateMatrix in a Transformation class).

    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
     jedoch
    -0.07
    hotmail
    -0.06
    lenir
    -0.06
    За
    -0.06
    avaş
    -0.06
     humanoid
    -0.06
    SKTOP
    -0.06
    _Pin
    -0.06
    amak
    -0.06
     лечение
    -0.06
    POSITIVE LOGITS
     tranqu
    0.07
     UICollectionView
    0.07
    ;amp
    0.07
     جل
    0.06
     الاح
    0.06
     strongest
    0.06
    ults
    0.06
     زي
    0.06
     أع
    0.06
     stranger
    0.06
    Activations Density 0.017%

    No Known Activations