© 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. 7769
    Prev
    Next
    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash

    This neuron detects Russian descriptive adjectives (especially evaluative ones like “важным,” “сильными,” “слабые” etc.).

    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
     toddlers
    -0.06
    (inflater
    -0.06
     cca
    -0.06
    ัวหน
    -0.06
     użytk
    -0.06
     center
    -0.06
     clinic
    -0.05
    nis
    -0.05
     Entre
    -0.05
     trung
    -0.05
    POSITIVE LOGITS
    цією
    0.08
    ам
    0.08
    ibus
    0.08
    BUM
    0.07
    zym
    0.07
    ительным
    0.07
    iem
    0.07
    лами
    0.07
    ями
    0.07
    Pokemon
    0.07
    Activations Density 0.075%

    No Known Activations