© 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. 13711
    Prev
    Next
    INDEX
    Explanations

    nitrogen and sulfur

    np_max-act · gemini-2.0-flash

    The neuron detects terms related to nutrient pollution in aquatic environments—especially words about nutrient loading (e.g. “nutrient,” “nitrogen,” “phosphorus,” “eutrophication”).

    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
     sincerity
    -0.06
     Host
    -0.06
     these
    -0.06
     {↵↵↵↵
    -0.06
     pagination
    -0.06
     toss
    -0.06
    filt
    -0.06
     flam
    -0.06
     اين
    -0.06
     Four
    -0.06
    POSITIVE LOGITS
     uLocal
    0.07
    öl
    0.06
     čas
    0.06
     орг
    0.06
    qp
    0.06
    ulf
    0.06
    (((
    0.06
    deer
    0.06
     دفاع
    0.06
     crib
    0.06
    Activations Density 0.005%

    No Known Activations