© 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. 13617
    Prev
    Next
    INDEX
    Explanations

    Atlantic/Halifax

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting mentions of geographic bodies of water or coastal region names (e.g. oceans, seas, specific coasts).

    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
     Em
    -0.07
     خوبی
    -0.06
    ract
    -0.06
     سپ
    -0.06
     OMIT
    -0.06
     ülkemiz
    -0.06
     cried
    -0.06
     mess
    -0.06
    暴
    -0.06
    css
    -0.06
    POSITIVE LOGITS
     Maine
    0.08
     Scotia
    0.06
     Phillies
    0.06
    τας
    0.06
     mlx
    0.06
    foundland
    0.06
    かに
    0.06
     patří
    0.06
     absorbs
    0.06
     enctype
    0.06
    Activations Density 0.024%

    No Known Activations