© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7239
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    specific military operations or actions involving naval vessels.

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

    This neuron fires most strongly on mentions of naval transits—when a ship “transited” a strait or sea passage.

    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
    _border
    -0.07
    hound
    -0.07
    Factors
    -0.06
    -stat
    -0.06
     ALPHA
    -0.06
     Hartford
    -0.06
    -ups
    -0.06
     Morr
    -0.06
     Minimum
    -0.06
     Destiny
    -0.06
    POSITIVE LOGITS
    .readlines
    0.07
    _generated
    0.06
    .HtmlControls
    0.06
    赏
    0.06
    /store
    0.06
    \Configuration
    0.06
     июля
    0.06
     Επι
    0.05
     hardships
    0.05
     ابراه
    0.05
    Activations Density 0.004%

    No Known Activations