© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85726
    Prev
    Next
    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash

    This neuron specifically lights up on German-language words or compound German terms (e.g. “Frontkämpferprivileg”).

    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
     Hayden
    -0.06
    under
    -0.06
     Diaz
    -0.06
    690
    -0.06
    })"↵
    -0.06
    asterxml
    -0.06
    |R
    -0.06
     Bryce
    -0.06
    适
    -0.06
    ception
    -0.06
    POSITIVE LOGITS
    .className
    0.07
     masse
    0.06
    uppies
    0.06
    ẵ
    0.06
     动
    0.06
     UIBarButtonItem
    0.06
    lack
    0.06
    UMMY
    0.06
     exceeds
    0.06
    Essay
    0.06
    Activations Density 0.146%

    No Known Activations