© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90589
    Prev
    Next
    INDEX
    Explanations

    go

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of import or package path identifiers (e.g. library/module import statements).

    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
     Air
    -0.07
     feet
    -0.06
    ी
    -0.06
     Eve
    -0.06
    ालत
    -0.06
     kötü
    -0.06
     REM
    -0.06
     Hort
    -0.06
    าล
    -0.06
     RECEIVE
    -0.06
    POSITIVE LOGITS
     staunch
    0.07
    .Rad
    0.07
    gregar
    0.07
     toxin
    0.07
     lar
    0.06
     minimized
    0.06
    	final
    0.06
    (ball
    0.06
     nargin
    0.06
     Restaurants
    0.06
    Activations Density 0.003%

    No Known Activations