© 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. 129889
    Prev
    Next
    INDEX
    Explanations

    gas

    np_max-act · gemini-2.0-flash

    The neuron activates whenever the text contains the word “gas” (especially in “natural gas”).

    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
    ebo
    -0.07
     leather
    -0.06
     Minute
    -0.05
     seen
    -0.05
     Sailor
    -0.05
     Lat
    -0.05
    รร
    -0.05
    reen
    -0.05
    との
    -0.05
    coll
    -0.05
    POSITIVE LOGITS
    /cat
    0.07
     imperative
    0.07
    _DATABASE
    0.07
    غيرة
    0.07
    PathParam
    0.07
     getType
    0.07
     aktual
    0.07
     inevitable
    0.07
     regiment
    0.07
     propane
    0.06
    Activations Density 0.007%

    No Known Activations