© 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. 7-RESID-POST-AA
    11. 47355
    Prev
    Next
    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of water or aquatic contexts—text describing bodies of water, swimming, boats, waves, or similar aquatic settings.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .MODEL
    -0.08
    Exclusive
    -0.06
     الثالث
    -0.06
    	task
    -0.06
    Transient
    -0.06
     mutations
    -0.06
    INS
    -0.06
     unprotected
    -0.06
     best
    -0.06
    -less
    -0.06
    POSITIVE LOGITS
     water
    0.09
     Water
    0.07
    -Semitism
    0.07
     WATER
    0.06
    Water
    0.06
     stairs
    0.06
    aph
    0.06
     Mitt
    0.06
    反
    0.06
     زنان
    0.06
    Activations Density 0.011%

    No Known Activations