© 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. 109842
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects location contexts, especially the preposition “in” and nearby place or region names.

    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
     �
    -0.06
    -</
    -0.06
     ogni
    -0.06
    Veter
    -0.06
    ourke
    -0.06
     soldier
    -0.06
     parçası
    -0.05
    isté
    -0.05
    usal
    -0.05
    circ
    -0.05
    POSITIVE LOGITS
    イン
    0.06
    _RENDERER
    0.06
    Recognition
    0.06
     Mandarin
    0.06
    /angular
    0.06
     Wifi
    0.06
    <O
    0.06
     Ability
    0.06
     qw
    0.06
    Bucket
    0.06
    Activations Density 0.007%

    No Known Activations