© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74793
    Prev
    Next
    INDEX
    Explanations

    warming

    np_max-act · gemini-2.0-flash

    The neuron fires on words derived from the root “ambient” (e.g. ambiente, ambiental, ambientale), i.e. environment‐related terms.

    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
    picable
    -0.08
    (entry
    -0.07
    需
    -0.07
    Sou
    -0.06
    (locations
    -0.06
    Resource
    -0.06
     upgrades
    -0.06
     Continuing
    -0.06
    Transformation
    -0.06
     Sinh
    -0.06
    POSITIVE LOGITS
     مان
    0.06
    ,number
    0.06
     vegetarian
    0.06
    .nextDouble
    0.06
     ferment
    0.06
    Included
    0.06
    oví
    0.06
    _Grid
    0.06
     Lastly
    0.06
     vac
    0.06
    Activations Density 0.018%

    No Known Activations