© 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. 89141
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of Philippine geographic place names (e.g., provinces, cities, towns, barangays).

    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
     الأح
    -0.06
     Takım
    -0.06
    _constants
    -0.06
    hcp
    -0.06
    _attach
    -0.06
    (mask
    -0.06
    teen
    -0.06
    _DIPSETTING
    -0.06
     обст
    -0.06
     Refriger
    -0.06
    POSITIVE LOGITS
     cuerpo
    0.07
    -len
    0.06
    <C
    0.06
     LOSS
    0.06
     played
    0.06
    .pages
    0.06
     쇼
    0.06
     htmlentities
    0.06
     protesting
    0.06
     Yatırım
    0.06
    Activations Density 0.036%

    No Known Activations