© 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. 44677
    Prev
    Next
    INDEX
    Explanations

    milk

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “milk.”

    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
    	UFUNCTION
    -0.08
     observer
    -0.07
    ंट
    -0.07
     persons
    -0.07
     stup
    -0.07
     हत
    -0.07
     เส
    -0.06
     Brendan
    -0.06
    _const
    -0.06
    _requested
    -0.06
    POSITIVE LOGITS
     milk
    0.16
     Milk
    0.14
    ilk
    0.09
     Silk
    0.08
     molecular
    0.07
     silk
    0.07
     ql
    0.07
    PV
    0.07
     Molecular
    0.07
     Liu
    0.07
    Activations Density 0.007%

    No Known Activations