© 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. 68968
    Prev
    Next
    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash

    The neuron activates on instances of the word “real,” especially when used as an intensifier or qualifier.

    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
    amburg
    -0.07
     simpler
    -0.06
    ıda
    -0.06
     coronary
    -0.06
     خواهد
    -0.06
    397
    -0.06
    [strlen
    -0.06
     domingo
    -0.06
    τιο
    -0.06
     glUniform
    -0.06
    POSITIVE LOGITS
     real
    0.13
     Real
    0.10
     REAL
    0.10
    Real
    0.10
    layers
    0.08
    -real
    0.07
     actual
    0.07
    	real
    0.07
    real
    0.07
     Dart
    0.07
    Activations Density 0.034%

    No Known Activations