© 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. 44195
    Prev
    Next
    INDEX
    Explanations

    displacement

    np_max-act · gemini-2.0-flash

    This neuron detects words referring to mechanical deformations or strain measurements (e.g., compression, displacement, elongation).

    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
     ethics
    -0.07
     �
    -0.06
    授
    -0.06
    увалися
    -0.06
    wed
    -0.06
     고려
    -0.06
     レ
    -0.06
     Macros
    -0.06
     whistle
    -0.06
    ASSWORD
    -0.06
    POSITIVE LOGITS
     серьез
    0.08
     Liberties
    0.07
     suất
    0.07
    @register
    0.06
     Frauen
    0.06
     rut
    0.06
     nông
    0.06
     Returns
    0.06
    空
    0.06
    šlo
    0.06
    Activations Density 0.047%

    No Known Activations